Interaction method, device, equipment and storage medium based on AIGC

Abstract

The present disclosure provides an interactive method, device, equipment and storage medium based on generative artificial intelligence AIGC, which relates to the field of artificial intelligence technology, specifically to the technical fields of human-computer interaction, AIGC, large models, etc. The interactive method based on generative artificial intelligence AIGC includes: generating a target pet model based on a real picture of the target pet and anthropomorphic attributes set by the user; generating anthropomorphic interactive content based on the target pet model; determining the interactive value of the target pet model based on the preset operation of the user for the target pet model; and interacting with the user based on the anthropomorphic interactive content and the interactive value. The present disclosure can enhance the emotional companionship effect of virtual pets.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to technical fields such as AIGC, large models, and human-computer interaction, and more particularly to an interaction method, apparatus, device, and storage medium based on AIGC. Background Art

[0002] With the development of artificial intelligence technology, virtual pets have emerged.

[0003] Generative AI (Artificial Intelligence Generated Content, AIGC) refers to a technology that generates relevant content with appropriate generalization capabilities through learning and identifying existing data based on artificial intelligence models such as generative adversarial networks and large pre-trained models. Summary of the Invention

[0004] The present disclosure provides an AIGC-based interaction method, apparatus, device, and medium.

[0005] According to one aspect of the present disclosure, an interaction method based on AIGC is provided, including: generating a target pet model based on a real picture of the target pet and anthropomorphic attributes set by a user; generating anthropomorphic interaction content based on the target pet model; determining an interaction value of the target pet model based on a preset operation of the user on the target pet model; and interacting with the user based on the anthropomorphic interaction content and the interaction value.

[0006] According to another aspect of the present disclosure, an AIGC-based interaction device is provided, including: a first generation module for generating a target pet model based on a real picture of the target pet and anthropomorphic attributes set by a user; a second generation module for generating anthropomorphic interaction content based on the target pet model; a determination module for determining the interaction value of the target pet model based on the user's preset operations on the target pet model; and an interaction module for interacting with the user based on the anthropomorphic interaction content and the interaction value.

[0007] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute any one of the methods described in any one of the above aspects.

[0008] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods according to any one of the above aspects.

[0009] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any one of the above aspects.

[0010] According to the technical solution disclosed in the present invention, the emotional companionship effect of the virtual pet can be improved.

[0011] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0013] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure;

[0014] Figure 2 is a schematic diagram of an application scenario for implementing an embodiment of the present disclosure;

[0015] Figure 3 is a schematic diagram of the overall architecture of an AIGC-based interactive system provided according to an embodiment of the present disclosure;

[0016] Figure 4 is a schematic diagram according to a second embodiment of the present disclosure;

[0017] Figure 5 is a schematic diagram of a training process of a target virtual pet model provided according to an embodiment of the present disclosure;

[0018] Figure 6 is a schematic diagram of a target pet model creation interface provided according to an embodiment of the present disclosure;

[0019] Figure 7 is a schematic diagram of a target pet model selection interface provided according to an embodiment of the present disclosure;

[0020] Figure 8 is a schematic diagram of an update interface of a target pet model provided according to an embodiment of the present disclosure;

[0021] Figure 9 is a schematic diagram of the main interface of the target pet model provided according to an embodiment of the present disclosure;

[0022] Figure 10 is a schematic diagram of an incoming mail interface of a target pet model provided according to an embodiment of the present disclosure;

[0023] Figure 11 This is a schematic diagram of generating letter content based on purchased props according to an embodiment of the present disclosure;

[0024] Figure 12 is a schematic diagram of various incoming letter contents provided according to an embodiment of the present disclosure;

[0025] Figure 13 is a schematic diagram of a photo-taking interface of a target pet model provided according to an embodiment of the present disclosure;

[0026] Figure 14 is a schematic diagram of a purchase interface provided according to an embodiment of the present disclosure;

[0027] Figure 15 is a schematic diagram according to a third embodiment of the present disclosure;

[0028] Figure 16 is a schematic diagram according to a fourth embodiment of the present disclosure;

[0029] Figure 17 is a schematic diagram according to a fifth embodiment of the present disclosure;

[0030] Figure 18 Schematic diagram of an electronic device for implementing the AIGC-based interaction method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0032] In related technologies, pet images rely on artificial design and are not personalized and realistic enough; virtual pets cannot have their own personalities and can only communicate with users according to set scripts.

[0033] In order to enhance the emotional companionship effect of virtual pets, the present disclosure provides the following embodiments.

[0034] Figure 1 is a schematic diagram according to a first embodiment of the present disclosure. This embodiment provides an AIGC-based interaction method, the method comprising:

[0035] 101. Generate a target pet model based on the real picture of the target pet and the anthropomorphic attributes set by the user.

[0036] 102. Generate anthropomorphic interactive content based on the target pet model.

[0037] 103. Determine an interaction value of the target pet model based on a preset operation of the user on the target pet model.

[0038] 104. Interact with the user based on the personified interaction content and the interaction value.

[0039] The real picture of the target pet can be uploaded by the user, and the user can use the photo of the pet he or she feeds in the real world as the real picture.

[0040] Anthropomorphic attributes refer to the personalized information that users assign to target pets, which may include name, gender, personality, etc. Personality may include being tsundere or clingy, etc.

[0041] The target pet model refers to a virtual pet that interacts with the user. The pet has anthropomorphic attributes so as to communicate with the user in an anthropomorphic manner.

[0042] Anthropomorphic interactive content refers to the anthropomorphic communication content between the target pet model and the user, such as: letters, instant conversations, photos, etc.

[0043] Generating a target pet model based on a real picture of the target pet can make the virtual pet image similar to the real picture, more personalized and realistic.

[0044] By giving anthropomorphic attributes such as personality to the target pet model, the user can make the virtual pet personalized and full of vitality, communicate with the user in an anthropomorphic way, and enhance the emotional connection.

[0045] The system corresponding to the target pet model can provide some basic operations, which can be called preset operations. By executing these preset operations, the user can affect the interaction value of the target pet model.

[0046] Preset operations include, for example, feeding, completing tasks, purchasing items, etc.

[0047] Interaction value refers to the value that influences the interaction between the target pet model and the user. Specifically, it can include intimacy, satiety, and mood. The interaction value is positively correlated with interaction frequency; that is, a higher interaction value indicates more frequent interactions. Specifically, higher intimacy, satiety, or mood indicates more frequent interactions between the target pet model and the user.

[0048] After obtaining the anthropomorphic interaction content and the interaction value, the target pet model can interact with the user (human) using the anthropomorphic interaction content based on the interaction frequency corresponding to the interaction value.

[0049] In this embodiment, a target pet model is generated based on a real picture of the target pet and anthropomorphic attributes set by the user, so that a more personalized and realistic virtual pet image can be obtained, and the target pet model can be given personalized characteristics and vitality. Anthropomorphic interactive content is generated based on the target pet model, and the user is interacted with based on the anthropomorphic interactive content and interactive value. This can enable the target pet model to have emotions and emotional expression capabilities without being limited to set scripts, thereby realizing anthropomorphic communication between the target pet model and the user, and enhancing the emotional companionship effect of the virtual pet.

[0050] In order to better understand the embodiments of the present disclosure, the application scenarios of the embodiments of the present disclosure are described below.

[0051] like Figure 2 As shown, a user can interact with the AIGC-based interactive system through a user terminal 201. User terminal 201 can be a personal computer (PC), a laptop, a mobile device (such as a mobile phone), etc. The main functional modules of the AIGC-based interactive system can be located on a server 202, which can be a local server or a cloud server, and can be a single server or a server cluster.

[0052] like Figure 3 As shown, the interactive system includes: a generation module 301, an interaction module 302, and an operation module 303. The generation module 301 mainly generates a target pet model based on the anthropomorphic attributes set by the user; the operation module 303 mainly obtains the user's preset operations on the target pet model and determines the interaction value of the target pet model based on the preset operations; the interaction module 302 mainly generates anthropomorphic interaction content based on the target pet model and interacts with the user based on the anthropomorphic interaction content and interaction value.

[0053] Interaction values ​​can include: intimacy, mood, satiety, etc. Figure 3 Take intimacy as an example.

[0054] The generation of the target pet model may include creating the target pet model and updating the target pet model. Figure 3 Take creating (updating) a pet as an example.

[0055] The target pet model can be generated based on a real picture of the target pet uploaded by the user; alternatively, the target pet model can be selected by the user from multiple pre-trained candidate pet models.

[0056] Real images can be stored in a network drive or a local hard drive, represented by network drive images and local images. After obtaining the real images, a target pet model can be generated based on generative artificial intelligence (AIGC). Because the real images uploaded by different users are different, a personalized target pet model can be generated, i.e., a user-specific pet model.

[0057] In addition, the user can set anthropomorphic attributes for the target pet model, for example, by inputting prompt information into the Large Language Model (LLM), which contains the anthropomorphic attributes of the target pet model to be generated, so that the target pet model with the anthropomorphic attributes can be generated based on AIGC.

[0058] AIGC refers to a technology that generates relevant content with appropriate generalization capabilities through learning and identifying existing data based on artificial intelligence models such as generative adversarial networks and large pre-trained models.

[0059] After generating the target pet model, anthropomorphic interactive content can be generated based on the target pet model. The anthropomorphic interactive content can also be generated based on AIGC. Figure 3 The AIGC-based core interaction representation is used. Anthropomorphic interaction methods include taking photos of pets, receiving pet letters, and having instant conversations with pets.

[0060] When taking photos of pets, AIGC can be used to generate pet photos based on theme templates; pet letters can be generated randomly with story-telling pictures and texts based on AIGC; and instant conversation content can be generated based on AIGC during instant conversations.

[0061] Preset operations include: obtaining tokens; purchasing items, completing tasks, feeding, pre-set game content (e.g., finding a kitten), etc. Tokens are represented by cans, specifically gold cans and purple cans. Different tokens can be obtained in different ways, for example, gold cans can be obtained by purchasing, and purple cans can be obtained by completing tasks.

[0062] The preset actions performed by the user will affect the interaction value. Figure 3 The interaction value is expressed as intimacy. The interaction value can affect the frequency of interaction between the virtual pet and the user, the virtual pet's travel, and the content of anthropomorphic interaction.

[0063] In combination with the above application scenarios, the present disclosure also provides an interaction method based on AIGC.

[0064] Figure 42 is a schematic diagram according to a second embodiment of the present disclosure. This embodiment provides an AIGC-based interaction method, the method comprising:

[0065] 401. Generate a target pet model based on the real picture of the target pet and the anthropomorphic attributes set by the user.

[0066] Among them, a large language model (LLM) can be used to generate a target pet model based on a real picture of the target pet and anthropomorphic attributes set by the user.

[0067] In this embodiment, the target pet model is generated based on LLM, and the excellent performance of LLM can be used to improve the model generation effect and enhance the user experience.

[0068] LLM has been a hot topic in the field of artificial intelligence in recent years. LLM is a pre-trained language model that has learned a wealth of language knowledge and world knowledge through pre-training on massive amounts of text data, enabling it to achieve amazing results in various natural language processing (NLP) and image processing tasks. Wenxin Yiyan, ChatGPT, and others are applications developed based on LLM. They can generate fluent, logical, and creative text content, and can even have natural conversations with humans. Specifically, taking text conversations as an example, large models can be general pre-trained Transformer (Generative Pre-trained Transformer, GPT) models based on Transformer, Enhanced Representation through Knowledge Integration (ERNIE) models based on knowledge integration, and so on.

[0069] For the generation of the target pet model, the large model can adopt a text-based graph or image-based graph model, specifically a StableDiffusion model. The Stable Diffusion model is an open source diffusion model that can generate target images through text descriptions or reference images. The Stable Diffusion model has multiple training methods. In this embodiment, the low-rank adaptation (LoRA) training method of a large language model is adopted. The LoRA training method can reduce the number of trainable parameters, reduce the storage space required for large models, and achieve efficient task switching.

[0070] like Figure 5As shown, for the real pictures of pets provided by different users (taking the first to third users as examples), the LoRA training method is used to obtain a pet model exclusive to each user.

[0071] The target pet model can be created based on a real picture of the target pet. Figure 6 As shown, users can trigger the creation process by clicking the "Create Your Own Pet" button. During this process, users upload a real picture of the target pet, and the target pet model is created based on the real picture. In addition, the creation process will generate anthropomorphic attributes of the pet by default, such as name, gender, and personality, which users can change.

[0072] The target pet model can also be selected from multiple candidate pet models that have been pre-trained. Figure 7 As shown, users can trigger the selection process by clicking the "Select One" button. During this process, the system provides multiple candidate pet models, and users can choose one as the target pet model based on their needs. In addition, the system will generate anthropomorphic attributes of the pet by default, such as name, gender, and personality, which users can change.

[0073] After the user creates or selects a target pet model, the target pet model can be modified. Figure 8 As shown, the user can recreate a pet or select a new one, and the user can change the anthropomorphic attributes of the pet.

[0074] The interface of the target pet model is as follows: Figure 9 As shown, the interface includes the following parts:

[0075] A: Background:

[0076] Including two layers: environment + pet body;

[0077] Pet themes are generated based on user-added photos;

[0078] The style effect is "realistic anthropomorphism", that is, the face of a real cat / dog and the clothes of the default style.

[0079] B: Pet information area

[0080] Pet avatar: generated based on user-added photos; click on the avatar area to view pet information;

[0081] name;

[0082] Number of cans owned: Initially, you have xx cans as a greeting gift;

[0083] Intimacy: Indicated by the heart under the avatar. Different levels of intimacy have different heart styles; there are 12 levels in total.

[0084] C: Interactive function area: letters, feeding, creative photos (see details below).

[0085] D: Content sedimentation area: memory wall.

[0086] E: Information reminder area: such as incoming letter reminder.

[0087] F: Commercial / operation area: stores, check-in (task system), settings, etc.

[0088] 402. Generate anthropomorphic interactive content based on the target pet model using LLM.

[0089] In this embodiment, LLM is used to generate the anthropomorphic interactive content, and the excellent performance of LLM can be used to improve the accuracy of the anthropomorphic interactive content.

[0090] Among them, the anthropomorphic interactive content mainly includes: taking photos, sending letters and instant conversations.

[0091] Specifically, LLM can be used to generate a photo of the target pet model based on the target pet model; or, LLM can be used to generate the content of an incoming letter based on the target pet model; or, LLM can be used to generate the content of an instant conversation based on the target pet model.

[0092] In this embodiment, by interacting with the virtual pet, such as taking photos, sending letters, and having instant conversations, a variety of anthropomorphic communication methods can be provided to enhance the interaction effect.

[0093] Virtual pets can actively write to users to report their daily lives, experiences outside, feelings, etc.

[0094] like Figure 10 As shown, when a letter comes in, a reminder message is displayed in the interface. After the user clicks the reminder message, the content of the letter is displayed. The content of the letter can include pictures, voice and text. Pictures can be saved or shared, and text can include the virtual pet's own language and the user's language. For example, if the virtual pet is a kitten, the virtual pet's own language is "meow", and the user's language is human language, such as Chinese.

[0095] In addition, the content of the letter may be related to the user's preset operation, and the preset operation may specifically be the props purchased by the user.

[0096] like Figure 11 As shown, the user can purchase props in the store. Assuming that the purchased props are music festival tickets, the content of the letter is related to the music festival.

[0097] In this embodiment, the content of the incoming letter is generated based on the user's preset operation, which can enrich the content of the incoming letter and improve the relevance of the content of the incoming letter to the user's operation.

[0098] In addition, the content of the letter may include graphic content, that is, it may include letter pictures and / or letter text, and the letter pictures are anthropomorphic story pictures generated based on the daily behavior of the target pet model (such as going to school, working, traveling, shopping, etc.); and / or, the letter text includes: the target pet model's own language text and user language text.

[0099] The content of the letter regarding different situations can be as follows Figure 12 As shown, the incoming images and text are related to the pet's behavior. For example, if the pet goes to the farm, farm-related images and text are generated. Furthermore, different images can form a story. For example, the second image is about flying, and the third image is about landing after the flight.

[0100] In this embodiment, anthropomorphic story images are generated based on the daily behavior of the target pet model. These images and text can be used to narrate the virtual pet's daily experiences, giving the virtual pet its own personality. The content of the letter can be generated based on this personality, rather than being limited to a set script, thereby enhancing the emotional interaction effect. In addition, the text includes text in the pet's language and the user's language, which can enhance the degree of anthropomorphism and readability, thereby improving the interaction effect.

[0101] For instant conversations, in response to an instant conversation triggered by a user, if the interaction value of the target pet model meets the preset conditions, LLM is used to generate instant conversation content based on the target pet model.

[0102] like Figure 10 As shown, the incoming message interface includes a "Chat" button. When the user clicks the button, the instant conversation process is triggered. If the interaction value of the target pet model meets the preset conditions, such as the mood value is greater than 0, the target pet model will have an instant conversation with the user. The instant conversation content of the target pet model can be generated using LLM.

[0103] In this embodiment, LLM can be used to conduct instant conversations with the target pet model, leveraging the superior performance of LLM to enhance the effectiveness of instant conversations. Furthermore, instant conversations are only conducted when the target pet model's interaction value meets a preset condition, encouraging the user to interact with the target pet model as much as possible, enhancing emotional connection.

[0104] For pet photography, LLM may be used to generate a photo of the target pet model based on the pet image of the target pet model and the theme template selected by the user.

[0105] like Figure 13As shown, the user can click the photo button in the interface where the target pet model is located to trigger the photo-taking process. The system can provide a variety of theme templates, such as evidence photos, birthday photos, etc., and the user can choose from the various theme templates provided by the system. Assuming that the selected theme template is evidence photos, a pet photo corresponding to the ID photo will be generated. During the photo-taking process, the progress can be displayed. By default, a preset number of photos (such as 4 photos) are generated each time; the generated photos can be saved to the network disk, downloaded locally, shared, etc. In addition, pet photos can be viewed through My Photos. My Photos is a photo-taking history record, displayed in reverse order: subject, photo-taking time; click to view details, long press to delete; a second pop-up window is required for confirmation when deleting; this entrance is not displayed when no photo is taken. In addition, theme templates can include free, paid, unlocked by intimacy, etc. In addition, the pet image can be updated, and the user can pay to update the pet image.

[0106] In this embodiment, a photo of the target pet model is generated based on the pet image and the theme template, which can provide the target pet model with an anthropomorphic photo-taking function and improve the interactive effect.

[0107] 403. Determine an interaction value of the target pet model based on a preset operation of the user on the target pet model.

[0108] The preset operations include, for example, feeding operations, purchasing operations, task operations, and the like.

[0109] Interaction values ​​include: satiety, mood, and intimacy.

[0110] Accordingly, based on the feeding operation, the satiety of the target pet model is determined; or, based on the purchasing operation, the mood value of the target pet model is determined; or, based on the task operation, the intimacy of the target pet model is determined.

[0111] In this embodiment, multiple interaction values ​​are determined based on multiple preset operations, which can provide more diverse interaction methods and enhance the interaction effect.

[0112] Specifically, regarding feeding: it supports feeding ordinary canned food and purchased snacks; when no food is available, you need to recharge or purchase; feeding can increase the pet's satiety and is beneficial for the pet's travel, and the more the pet travels, the richer the content of the letter can be.

[0113] Regarding purchases: users can influence their pets’ moods by purchasing props; for example, giving a kitten cat grass will increase its mood; giving a dog a subway ticket will allow the dog to take the subway home; props are divided into two categories: permanent and consumable, for example, concert tickets are consumable, and hats are permanent. In addition, props can also affect the content of incoming letters, for example, if you buy concert tickets, the content of the letter will be pictures and text about the concert. Figure 14As shown, users can purchase snacks, props, etc. in the store. In addition, the corresponding interaction value change information can be displayed based on the purchased snacks or props. For example, after purchasing mood props, the mood value can be displayed as increased.

[0114] For tasks: Check-in tasks: Increase intimacy; Daily tasks: Earn free purple cans. As intimacy increases, letters can be sent more frequently.

[0115] 404. Determine an interaction frequency based on the interaction value, and display the anthropomorphic interaction content to the user based on the interaction frequency.

[0116] The interaction value can be positively correlated with the interaction frequency. For example, if the interaction value is intimacy, the higher the intimacy, the higher the interaction frequency. After generating anthropomorphic interaction content based on LLM, the interaction frequency can be used to display it to the user, thereby conducting anthropomorphic communication with the user.

[0117] In this embodiment, the interaction frequency is determined based on the interaction value, which can trigger the user to perform more operations such as feeding with the virtual pet, thereby improving the interaction effect.

[0118] Figure 15 is a schematic diagram according to a third embodiment of the present disclosure. This embodiment provides an AIGC-based interaction method, the method comprising:

[0119] 1501. Using LLM, a target pet model is generated based on the real picture of the target pet and the anthropomorphic attributes set by the user.

[0120] Among them, this embodiment takes the use of LLM to generate the target pet model as an example, and other methods can also be used, such as a specially trained generation model to generate the target pet model based on the real picture of the target pet and the anthropomorphic attributes set by the user.

[0121] In this embodiment, the target pet model is generated based on the LLM, and the excellent performance of the LLM can be utilized to improve the generation effect of the target pet model and enhance the user experience.

[0122] 1502. Based on AIGC, generate the content of the letter according to the daily behavior of the target pet model.

[0123] Among them, AIGC refers to a technology that generates relevant content with appropriate generalization capabilities through learning and identifying existing data based on artificial intelligence models such as generative adversarial networks and large pre-trained models.

[0124] Examples of daily activities include studying, working, and traveling.

[0125] Specifically, the daily behavior of the target pet model can be determined based on the anthropomorphic growth line behavior. For example, if a person studies first and then works, the daily behavior of the target pet model is also to study first and then work.

[0126] In this embodiment, the daily behavior of the target pet model is determined based on the anthropomorphic growth line behavior, so that the target pet model can better simulate human behavior and enhance the anthropomorphic interaction effect.

[0127] The content of the letter includes: a letter picture and / or a letter text, the letter picture is an anthropomorphic story picture generated based on the daily behavior, and the letter text includes: the target pet model's own language text and the user language text.

[0128] For example, reference Figure 12 The incoming pictures and text are related to the pet's behavior. For example, if the pet goes to the farm, pictures and text related to the farm will be generated. In addition, different pictures can form a story. For example, the second picture is about flying, and the third picture is about landing after the flight.

[0129] In this embodiment, anthropomorphic story images are generated based on the daily behavior of the target pet model. These images and text can be used to narrate the virtual pet's daily experiences, giving the virtual pet its own personality. The content of the letter can be generated based on this personality, rather than being limited to a set script, thereby enhancing the emotional interaction effect. In addition, the text includes text in the pet's language and the user's language, which can enhance the degree of anthropomorphism and readability, thereby improving the interaction effect.

[0130] In addition, the content of the letter can also be randomly determined based on the behavior of the target pet model, and the letter content can be generated based on the randomly determined behavior and the target pet model. For example, if the daily behavior is "travel", the travel destination can be randomly determined, and then the corresponding letter content can be generated based on the randomly determined destination.

[0131] In this embodiment, by randomly determining the behavioral content of the target pet model's daily behavior and generating the content of the letter based on the behavioral content, the randomness of the content of the letter can be improved, thereby enhancing the interaction effect.

[0132] 1503. Determine the interaction value of the target pet model based on the user's preset operation on the target pet model.

[0133] 1504. Determine the frequency of incoming letters based on the interaction value, and determine the time of incoming letters according to the frequency of incoming letters; and, at the time of incoming letters, display the content of the incoming letters to the user.

[0134] The interaction value is positively correlated with the interaction frequency, meaning that higher the interaction value, the more frequent the interaction. Specifically, higher intimacy, higher satiety, or higher mood values ​​indicate more frequent interactions between the target pet model and the user.

[0135] The correspondence between the interaction value and the frequency of incoming letters can be pre-configured, and the frequency of incoming letters can be determined based on the correspondence. Then, the corresponding incoming letter time can be determined based on the incoming letter frequency, so that at the incoming letter time, the target pet model sends a letter to the user and the content of the letter is displayed to the user.

[0136] In this embodiment, the interaction frequency is determined based on the interaction value, which can trigger the user to perform more operations such as feeding with the virtual pet, thereby improving the interaction effect.

[0137] Based on the above example, the virtual pet (target pet model) can actively send a letter to the user, and the user can reply. Alternatively, the user can have an instant conversation with the virtual pet.

[0138] Figure 16 is a schematic diagram according to a fourth embodiment of the present disclosure. This embodiment provides an AIGC-based interaction method, the method comprising:

[0139] 1601. Using LLM, a target pet model is generated based on the real picture of the target pet and the anthropomorphic attributes set by the user.

[0140] 1602. Based on AIGC, generate the content of the letter according to the daily behavior of the target pet model.

[0141] 1603. Determine the interaction value of the target pet model based on the user's preset operation on the target pet model.

[0142] 1604. Determine the frequency of incoming letters based on the interaction value, and determine the time of incoming letters according to the frequency of incoming letters; and, at the time of incoming letters, display the content of the incoming letters to the user.

[0143] 1605. In response to the user clicking an instruction on a reply button on the interactive interface where the content of the incoming letter is located, a reply interface is displayed to the user, and the reply content entered by the user in the reply interface is received.

[0144] For example, reference Figure 12 The interactive interface containing the incoming message includes a reply button, represented by "Reply." Clicking this button displays a reply interface where the user can enter their reply and send it to the virtual pet. The virtual pet can then generate new incoming messages based on the user's reply and display them to the user, enabling communication between the user and the virtual pet.

[0145] In this embodiment, by displaying the reply interface, the user can reply to the virtual pet, thereby realizing letter exchange between the user and the virtual pet.

[0146] In some embodiments, after step 1604, the interaction method may further include:

[0147] 1606. In response to a user clicking instruction on a chat button on the interactive interface where the content of the incoming letter is located, if the interaction value meets a preset condition, a chat interface is displayed to the user, and chat content input by the user in the chat interface is received.

[0148] For example, reference Figure 12 The interactive interface containing the incoming message content includes a chat button, represented by "Chat Chat". After the user clicks the chat button, if the interaction value meets the preset conditions (such as the virtual pet's mood value is greater than 0), the user can chat with the virtual pet, that is, a chat interface can be displayed, and the user can enter the chat content in the chat interface. The chat content of the virtual pet can be generated based on AIGC, according to the conversation context, the personality of the virtual pet, etc.

[0149] In this embodiment, by displaying a chat interface, the user can have an instant conversation with the virtual pet.

[0150] Figure 17 17 is a schematic diagram of the fifth embodiment of the present disclosure. This embodiment provides an interactive device based on AIGC. The device 1700 includes: a first generating module 1701, a second generating module 1702, a determining module 1703 and an interactive module 1704.

[0151] The first generation module 1701 is used to generate a target pet model based on a real picture of the target pet and the anthropomorphic attributes set by the user; the second generation module 1702 is used to generate anthropomorphic interaction content based on the target pet model; the determination module 1703 is used to determine the interaction value of the target pet model based on the user's preset operations on the target pet model; the interaction module 1704 is used to interact with the user based on the anthropomorphic interaction content and the interaction value.

[0152] In this embodiment, a target pet model is generated based on the anthropomorphic attributes set by the user, which can give the target pet model personalized characteristics and vitality, generate anthropomorphic interactive content based on the target pet model, and interact with the user based on the anthropomorphic interactive content and interactive value, so that the target pet model has emotions and emotional expression capabilities, realizes anthropomorphic communication between the target pet model and the user, and improves the interactive effect.

[0153] In some embodiments, the first generating module 1701 is further configured to: generate a target pet model using LLM based on a real picture of the target pet and anthropomorphic attributes set by the user.

[0154] In this embodiment, a target pet model is generated based on a real picture of the target pet, which can obtain a personalized pet image, improve the model generation effect, and enhance the user experience.

[0155] In some embodiments, the second generating module 1702 is further configured to: generate anthropomorphic interactive content based on the target pet model using LLM.

[0156] In this embodiment, LLM is used to generate the anthropomorphic interactive content, and the excellent performance of LLM can be used to improve the accuracy of the anthropomorphic interactive content.

[0157] In some embodiments, the second generation module 1702 is further used to perform at least one of the following items: using LLM to generate the content of the letter based on the target pet model; using LLM to generate the content of the instant conversation based on the target pet model; using LLM to generate a photo of the target pet model based on the target pet model.

[0158] In this embodiment, by interacting with the virtual pet, such as taking photos, sending letters, and having instant conversations, a variety of anthropomorphic communication methods can be provided to enhance the interaction effect.

[0159] In some embodiments, the second generating module 1702 is further configured to: adopt LLM based on the target pet model and the user's preset operation.

[0160] In this embodiment, the content of the incoming letter is generated based on the user's preset operation, which can enrich the content of the incoming letter and improve the relevance of the content of the incoming letter to the user's operation.

[0161] In some embodiments, the content of the letter includes:

[0162] Incoming letter pictures, wherein the incoming letter pictures are personified story pictures generated based on the daily behavior of the target pet model; and / or incoming letter text, wherein the incoming letter text includes: the target pet model's own language text and the user language text.

[0163] In this embodiment, anthropomorphic story pictures are generated based on the daily behavior of the target pet model. The pictures and text can be used to narrate the daily experiences of the virtual pet, so that the virtual pet has its own personality and can actively generate the content of the letter based on its own personality, rather than being limited to the set script, thereby enhancing the emotional interaction effect.

[0164] In some embodiments, the second generating module 1702 is further configured to: generate a photo of the target pet model based on the pet image of the target pet model and the theme template selected by the user using LLM.

[0165] In this embodiment, a photo of the target pet model is generated based on the pet image and the theme template, which can provide the target pet model with an anthropomorphic photo-taking function and improve the interactive effect.

[0166] In some embodiments, the preset operations include: feeding operations, purchasing operations and task operations; accordingly, the interaction values ​​include: satiety, mood value and intimacy; the determination module 1703 is further used to: determine the satiety of the target pet model based on the feeding operation; or, determine the mood value of the target pet model based on the purchasing operation; or, determine the intimacy of the target pet model based on the task operation.

[0167] In this embodiment, multiple interaction values ​​are determined based on multiple preset operations, which can provide more diverse interaction methods and enhance the interaction effect.

[0168] In some embodiments, the second generation module 1702 is further used to: generate letter content based on AIGC according to the daily behavior of the target pet model, the letter content includes: letter pictures and / or letter text, the letter pictures are personified story pictures generated based on the daily behavior, and the letter text includes: the target pet model's own language text and the user language text; accordingly, the interaction module 1704 is further used to: determine the frequency of letters based on the interaction value, and determine the time of letters according to the frequency of letters; at the time of letters, display the content of the letter to the user.

[0169] In some embodiments, the second generating module 1702 is further configured to determine the daily behavior of the target pet model based on the anthropomorphic growth line behavior.

[0170] In this embodiment, the daily behavior of the target pet model is determined based on the anthropomorphic growth line behavior, so that the target pet model can better simulate human behavior and enhance the anthropomorphic interaction effect.

[0171] In some embodiments, the second generating module 1702 is further used to: randomly determine the behavioral content of the daily behavior; and generate the content of the letter based on the target pet model and the behavioral content.

[0172] In this embodiment, by randomly determining the behavioral content of the target pet model's daily behavior and generating the content of the letter based on the behavioral content, the randomness of the content of the letter can be improved, thereby enhancing the interaction effect.

[0173] In some embodiments, the interactive interface where the content of the incoming letter is located includes: a reply button; the interactive module 1704 is also used to: in response to the user's click instruction on the reply button, display the reply interface to the user, and receive the reply content entered by the user in the reply interface.

[0174] In this embodiment, by displaying the reply interface, the user can reply to the virtual pet, thereby realizing letter exchange between the user and the virtual pet.

[0175] In some embodiments, the interactive interface where the content of the incoming letter is located includes: a chat button; the interactive module 1704 is also used to: respond to the user's click instruction on the chat button, if the interaction value meets the preset conditions, display the chat interface to the user, and receive the chat content entered by the user in the chat interface.

[0176] In this embodiment, by displaying a chat interface, the user can have an instant conversation with the virtual pet.

[0177] It can be understood that in the embodiments of the present disclosure, the same or similar contents in different embodiments can be referenced to each other.

[0178] It can be understood that the terms “first”, “second”, etc. in the embodiments of the present disclosure are only used for distinction and do not indicate the degree of importance, time sequence, etc.

[0179] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0180] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0181] Figure 18 A schematic block diagram of an example electronic device 1800 that can be used to implement embodiments of the present disclosure is shown. Electronic device 1800 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 1800 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0182] like Figure 18As shown, electronic device 1800 includes a computing unit 1801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1802 or a computer program loaded from a storage unit 1808 into a random access memory (RAM) 1803. Various programs and data required for the operation of electronic device 1800 can also be stored in RAM 1803. Computing unit 1801, ROM 1802, and RAM 1803 are connected to each other via a bus 1804. An input / output (I / O) interface 1805 is also connected to bus 1804.

[0183] Multiple components in electronic device 1800 are connected to I / O interface 1805, including: an input unit 1806, such as a keyboard, mouse, etc.; an output unit 1807, such as various types of displays, speakers, etc.; a storage unit 1808, such as a magnetic disk, optical disk, etc.; and a communication unit 1809, such as a network card, modem, wireless communication transceiver, etc. The communication unit 1809 allows electronic device 1800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0184] The computing unit 1801 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 1801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1801 performs the various methods and processes described above, such as the AIGC-based interaction method. For example, in some embodiments, the AIGC-based interaction method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 1808. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 1800 via the ROM 1802 and / or the communication unit 1809. When the computer program is loaded into the RAM 1803 and executed by the computing unit 1801, one or more steps of the AIGC-based interaction method described above can be performed. Alternatively, in other embodiments, the computing unit 1801 may be configured to execute the AIGC-based interaction method in any other appropriate manner (eg, by means of firmware).

[0185] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0186] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable load balancing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0187] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0188] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0189] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0190] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. This client-server relationship is established by computer programs running on the respective computers, establishing a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosts and VPS services ("Virtual Private Servers" or simply "VPS"). The server may also be a server in a distributed system or a server integrated with blockchain.

[0191] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0192] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. An interactive method based on generative artificial intelligence AIGC, comprising: Generate a target pet model based on the real picture of the target pet and the anthropomorphic attributes set by the user; The target pet model is generated by the large model LLM based on AIGC according to the input anthropomorphic attributes, and the anthropomorphic attributes include personality; Based on the target pet model, generating anthropomorphic interactive content; Determining the interaction value of the target pet model based on the preset operation of the user on the target pet model; interacting with the user based on the personified interaction content and the interaction value; The anthropomorphic interaction content includes: the content of the letter; The content of the letter is generated based on AIGC according to the randomly determined behavior content corresponding to the target pet model and the daily behavior of the target pet model, and the daily behavior is determined based on the anthropomorphic growth line behavior sequence.

2. The method according to claim 1, wherein: The generating of anthropomorphic interactive content based on the target pet model further includes at least one of the following items: Using LLM, based on the target pet model, generating instant conversation content; Using LLM, a photo of the target pet model is generated based on the target pet model.

3. The method according to claim 2, wherein: The step of using LLM to generate a photo of the target pet model based on the target pet model includes: Using LLM, a photo of the target pet model is generated based on the pet image of the target pet model and the theme template selected by the user.

4. The method according to claim 1, wherein: The content of the letter includes: a letter picture and / or a letter text, wherein the letter picture is an anthropomorphic story picture generated based on the daily behavior, and the letter text includes: the target pet model's own language text and the user language text; Accordingly, the interacting with the user based on the anthropomorphic interaction content and the interaction value includes: Based on the interaction value, determine the frequency of incoming letters, and determine the time of incoming letters according to the frequency of incoming letters; At the time of the incoming letter, the content of the incoming letter is displayed to the user.

5. The method according to claim 4, wherein: The interactive interface where the letter content is located includes: a reply button; After displaying the content of the incoming letter to the user at the time of the incoming letter, the interacting with the user based on the anthropomorphic interaction content and the interaction value further includes: In response to a user clicking instruction on the reply button, a reply interface is displayed to the user, and reply content input by the user in the reply interface is received.

6. The method according to claim 4, wherein: The interactive interface where the content of the letter is located includes: a chat button; After displaying the content of the incoming letter to the user at the time of the incoming letter, the interacting with the user based on the anthropomorphic interaction content and the interaction value further includes: In response to a user's click instruction on the chat button, if the interaction value meets a preset condition, a chat interface is displayed to the user, and chat content input by the user in the chat interface is received.

7. The method according to claim 1, wherein: The preset operations include: feeding operation, purchasing operation and task operation; correspondingly, the interaction values ​​include: satiety, mood value and intimacy; The step of determining the interaction value of the target pet model based on the preset operation of the user on the target pet model comprises: Based on the feeding operation, determining the satiety of the target pet model; or, Based on the purchase operation, determining the mood value of the target pet model; or, Based on the task operation, the intimacy of the target pet model is determined.

8. An interactive device based on generative artificial intelligence AIGC, comprising: A first generation module, used to generate a target pet model according to a real picture of the target pet and anthropomorphic attributes set by a user; The target pet model is generated by the large model LLM based on AIGC according to the input anthropomorphic attributes, and the anthropomorphic attributes include personality; A second generating module, used for generating anthropomorphic interactive content according to the target pet model; A determination module, configured to determine the interaction value of the target pet model according to a preset operation of the user on the target pet model; An interaction module, configured to interact with the user according to the anthropomorphic interaction content and the interaction value; The anthropomorphic interaction content includes: the content of the letter; The content of the letter is generated based on AIGC according to the randomly determined behavior content corresponding to the target pet model and the daily behavior of the target pet model, and the daily behavior is determined based on the anthropomorphic growth line behavior sequence.

9. The device according to claim 8, wherein: The second generation module is further configured to perform at least one of the following: Using LLM, based on the target pet model, generating instant conversation content; Using LLM, a photo of the target pet model is generated based on the target pet model.

10. The device according to claim 9, wherein: The second generating module is further used for: Using LLM, a photo of the target pet model is generated based on the pet image of the target pet model and the theme template selected by the user.

11. The device according to claim 8, wherein: The content of the letter includes: a letter picture and / or a letter text, wherein the letter picture is an anthropomorphic story picture generated based on the daily behavior, and the letter text includes: the target pet model's own language text and the user language text; Accordingly, the interaction module is further used for: Based on the interaction value, determine the frequency of incoming letters, and determine the time of incoming letters according to the frequency of incoming letters; At the time of the incoming letter, the content of the incoming letter is displayed to the user.

12. The device according to claim 11, wherein The interactive interface where the letter content is located includes: a reply button; The interaction module is also used for: In response to a user clicking instruction on the reply button, a reply interface is displayed to the user, and reply content input by the user in the reply interface is received.

13. The device according to claim 11, wherein: The interactive interface where the content of the letter is located includes: a chat button; The interaction module is also used for: In response to a user's click instruction on the chat button, if the interaction value meets a preset condition, a chat interface is displayed to the user, and chat content input by the user in the chat interface is received.

14. The device according to claim 8, wherein: The preset operations include: feeding operation, purchasing operation and task operation; correspondingly, the interaction values ​​include: satiety, mood value and intimacy; The determination module is further used for: Based on the feeding operation, determining the satiety of the target pet model; or, Based on the purchase operation, determining the mood value of the target pet model; or, Based on the task operation, the intimacy of the target pet model is determined.

15. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

17. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images