Avatar-based interaction method and apparatus
By using virtual avatars to determine promotional conditions based on artificial intelligence models during interactions, promotional content can be accurately delivered, solving the problem of information overload in internet advertising and achieving efficient and precise promotional results.
Patent Information
- Application Number
- PCT/CN2026/094938
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-05-09
- Filing Date
- 2026-05-06
- Publication Date
- 2026-11-12
AI Technical Summary
Information overload in internet advertising leads to poor advertising results, making it difficult to achieve precise and efficient promotion.
By using virtual avatars based on artificial intelligence models during interactions, promotional conditions are determined based on the content and responses of the interactions, and promotional content is accurately released, including text, voice, emoticons, and action responses.
It significantly improved the accuracy and efficiency of promotion, reduced the waste of advertising resources, and increased click-through rate and conversion rate.
Smart Images

Figure CN2026094938_12112026_PF_FP_ABST
Abstract
Description
Virtual avatar-based interaction method and device
[0001] Cross-reference to Related Applications
[0002] The present disclosure claims priority to the Chinese patent application No. 202510594615X entitled "Virtual avatar-based interaction method and device" filed on May 09, 2025 with the China Patent Office, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD
[0003] The present disclosure relates to the technical field of interaction, and in particular, to a virtual avatar-based interaction method and device. BACKGROUND
[0004] In order to better promote and popularize products, creative promotion of products is usually adopted. Creative promotion is the core strategy for enterprises to improve product awareness, shape brand image and promote sales conversion. Its essence lies in deeply binding product value and consumer demand through unique creative ideas, triggering emotional resonance with differentiated content, and breaking through the communication barriers in the information overload era.
[0005] Currently, in order to better promote and popularize products, creative advertising promotion of products on the Internet is usually adopted. Users can view relevant information about products according to the creative advertising on the Internet.
[0006] There is a large amount of information on the Internet, and users will be exposed to a large amount of advertising content every day. Due to the large amount of information, advertisements are easily submerged in the information ocean and cannot effectively attract user attention, resulting in poor advertising effect and difficulty in achieving precise and efficient advertising push.
[0007] SUMMARY
[0008] The present disclosure provides a virtual avatar-based interaction method and device, which significantly improves the accuracy and efficiency of promotion by accurately publishing promotion content in the interaction process of a target virtual avatar.
[0009] According to an aspect of the present disclosure, a virtual avatar-based interaction method is provided, which includes:
[0010] obtaining a target virtual avatar; in response to receiving at least one piece of interaction content, the target virtual avatar outputs at least one piece of interaction response based on an artificial intelligence model for the at least one piece of interaction content, the interaction response including one or more of a text reply, a voice reply, an expression reply, and a motion reply;
[0011] In response to the interaction content and / or the interaction response reaching a promotion condition, the target virtual image publishes promotion content in the interaction response; wherein the promotion condition is configured to represent a condition for the target virtual image to publish the promotion content.
[0012] According to another aspect of the present disclosure, an interaction device based on a virtual image is provided, the device comprising:
[0013] a target virtual image obtaining module configured to obtain a target virtual image; in response to receiving at least one piece of interaction content, the target virtual image outputs at least one piece of interaction response based on an artificial intelligence model for the at least one piece of interaction content, the interaction response comprising one or more of a text reply, a voice reply, an expression reply, and a motion reply;
[0014] a promotion content publishing module configured to, in response to the interaction content and / or the interaction response reaching a promotion condition, the target virtual image publishing promotion content in the interaction response; wherein the promotion condition is configured to represent a condition for the target virtual image to publish the promotion content.
[0015] According to another aspect of the present disclosure, an electronic device is provided, the electronic device comprising:
[0016] at least one processor; and a memory communicatively connected with the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform an interaction method based on a virtual image according to any one of the embodiments of the present disclosure.
[0017] According to another aspect of the present disclosure, a computer readable storage medium is provided, the computer readable storage medium storing computer instructions for enabling a processor to implement an interaction method based on a virtual image according to any one of the embodiments of the present disclosure when executed by the processor.
[0018] The technical solution of the embodiments of the present disclosure is to obtain a target virtual image, and then in response to the interaction content and / or the interaction response reaching a promotion condition, the target virtual image publishes promotion content in the interaction response. This technical solution, based on an artificial intelligence large model, accurately determines and publishes promotion content by the target virtual image in its interaction with the user, significantly improving the accuracy and efficiency of promotion.
[0019] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS
[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description only constitute some of the embodiments of the present disclosure, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.
[0021] FIG. 1 is a flow chart of a virtual image-based interaction method according to an embodiment of the present disclosure;
[0022] FIG. 2 is a schematic diagram of a virtual image-based interaction process according to an embodiment of the present disclosure;
[0023] FIG. 3 is a flow chart of a virtual image-based interaction process according to an embodiment of the present disclosure;
[0024] FIG. 4 is a schematic diagram of a virtual image-based interaction process according to an embodiment of the present disclosure;
[0025] FIG. 5 is a structural schematic diagram of a virtual image-based interaction device according to an embodiment of the present disclosure;
[0026] FIG. 6 is a structural schematic diagram of an electronic device implementing a virtual image-based interaction method according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0027] In order to make the person skilled in the art better understand the present disclosure scheme, the following will combine the drawings in the embodiments of the present disclosure, and clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present disclosure.
[0028] It should be noted that the terms "first", "second", and the like in the specification and claims of the present disclosure and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.
[0029] FIG. 1 is a flowchart of a virtual image-based interaction method according to an embodiment of the present disclosure. The embodiment can be applied to a case where a virtual image is used to publish promotional content in an interaction process. The method can be performed by a virtual image-based interaction device, which can be implemented in hardware and / or software and can be configured in a device, such as a background server or other device with communication and computing capabilities. As shown in FIG. 1, the method includes the following steps:
[0030] In S110, a target virtual image is obtained. In response to receiving at least one piece of interaction content, the target virtual image outputs at least one piece of interaction response based on an artificial intelligence model for the at least one piece of interaction content. The interaction response includes one or more of a text reply, a voice reply, an expression reply, and a motion reply.
[0031] In the present solution, the target virtual image refers to a virtual character with visual image created by digital technology, which can be presented in different media, such as movies, animations, games, etc. The target virtual image is generated by an artificial intelligence model. The artificial intelligence model is a generative artificial intelligence large model or a deep learning model.
[0032] The interaction content refers to various information, elements, or data involved in the interaction process. The interaction content includes at least the text entered by the target object in the system interface input box, the audio information collected by the voice recognition system of the target object, and the instruction signal triggered by the target object clicking the button or sliding the screen.
[0033] In the present embodiment, the interaction response refers to the answer to the interaction content issued by the target object in an interaction. The interaction response includes one or more of a text reply, a voice reply, an expression reply, and a motion reply.
[0034] Optionally, at least one piece of interaction content sent by the target object is obtained based on the artificial intelligence model, and the at least one piece of interaction content is analyzed and processed to generate at least one piece of interaction response.
[0035] In S120, in response to the interaction content and / or the interaction response meeting a promotional condition, the target virtual image publishes promotional content in the interaction response. The promotional condition is used to represent the condition for the target virtual image to publish the promotional content.
[0036] In the embodiment, the promotion content refers to information about a product delivered to a target object through various media. The product refers to anything that can be provided to the market, used and consumed by people, and meet the needs of people, including physical products and virtual programs. The physical product refers to a product with a physical form, such as a mobile phone, a car, food, clothing, etc. The virtual program refers to a program or software in digital form, such as an operating system, office software, games, mobile applications, etc.
[0037] In the scheme, the promotion condition is used to represent the condition for the target virtual image to publish the promotion content. The promotion condition is a keyword of the promotion content detected in the interactive content; or the promotion condition is information related to the promotion content detected in the interactive content; or the promotion condition is that the interaction time length of the target virtual image in the current conversation reaches a preset interaction time length threshold; or the promotion condition is that the interaction times of the target virtual image in the current conversation reaches a preset interaction times threshold.
[0038] Optionally, the interactive content and the interaction response are judged, and when at least one of the interactive content and the interaction response reaches the promotion condition, the target virtual image publishes the promotion content in the interaction response with the target object.
[0039] In the scheme, the target virtual image has diversified interaction functions, not only accurately implanting the promotion content in the real-time interaction with the target object to achieve natural touch of marketing information, but also focusing on the conversation with the target object, quickly responding and professionally answering various questions raised by the target object based on the knowledge reserve and intelligent algorithm, and providing personalized interactive service experience.
[0040] Optionally, the promotion condition includes:
[0041] The first matching rate of at least one piece of interactive content to at least one product in the preset promotion product database is greater than or equal to a preset promotion threshold, the interaction time length of the target virtual image in the current conversation reaches a preset interaction time length threshold, and the interaction times of the target virtual image in the current conversation reaches a preset interaction times threshold.
[0042] In the scheme, the promotion threshold, the interaction time length threshold, and the interaction times threshold can be set by the virtual image generation object in the virtual image generation step, or can be adjusted in real time after the virtual image is generated; when the virtual image generator does not set the above parameters, the artificial intelligence model can also infer the parameters according to historical data.
[0043] The first matching rate is determined based on an artificial intelligence model.
[0044] In the embodiment, the promotion product database is set by the virtual image generation object in advance. The promotion product database covers various types of products.
[0045] Optionally, the first matching rate of the at least one piece of interaction content and each product in the preset promoted product database is calculated based on the artificial intelligence model, and when the first matching rate is greater than or equal to a promotion threshold, it is determined that the promotion condition is met.
[0046] In this embodiment, the interaction duration of the target virtual image in the current dialogue is calculated in real time based on the artificial intelligence model, and when the interaction duration reaches an interaction duration threshold, it is determined that the promotion condition is met.
[0047] In this embodiment, the interaction times of the target virtual image in the current dialogue are counted based on the artificial intelligence model, and when the interaction duration reaches an interaction times threshold, it is determined that the promotion condition is met.
[0048] When the interaction content and interaction response of the target object and the target virtual image meet the promotion condition, the target virtual image publishes customized promotion content. The customized promotion content is generated by the artificial intelligence model, which deeply analyzes the behavior data of the target object to ensure that the promotion content is highly consistent with the interests of the target object. Not only does it greatly improve the relevance and appeal of the promotion content, effectively improving the click-through rate and conversion rate of the target object, but also through the data-driven precise touch mode, it significantly optimizes the promotion delivery efficiency. At the same time, relying on the diversified presentation form of the target virtual image, the product information can be displayed in a more technological way, strengthening the core of the product, and avoiding the waste of resources in traditional wide-area delivery, effectively reducing the cost loss caused by invalid exposure.
[0049] Optionally, the generation process of the promotion content includes:
[0050] The third parameter is obtained, and the third parameter at least includes a to-be-promoted product keyword;
[0051] The third parameter is taken as input, and at least one piece of promotion content is output based on the artificial intelligence model; wherein the promotion content is at least one of text type, audio type, video type, and image type.
[0052] In this scheme, the third parameter at least includes a to-be-promoted product keyword, and the to-be-promoted product keyword refers to a series of product-related words selected and determined before the product promotion activity. For example, the to-be-promoted product keyword at least includes the product name, product category, use, product image, and brand.
[0053] In this embodiment, the corresponding data is automatically collected and extracted to generate the third parameter by responding to the input operation of the virtual image generation object in the system interface in real time; or the third parameter is obtained by using image analysis technology to identify features and analyze data of the to-be-promoted product picture uploaded by the virtual image generation object.
[0054] Optionally, the product keyword to be promoted is taken as input, and the product keyword to be promoted is analyzed and processed based on the artificial intelligence model to output at least one piece of promotion content.
[0055] The third parameter further includes common advertisement parameters in an advertisement generation process, such as an advertisement plot and an advertisement scene.
[0056] Optionally, at least one of the product keyword to be promoted and the advertisement plot and the advertisement scene is taken as input, and the at least one of the product keyword to be promoted and the advertisement plot and the advertisement scene is analyzed and processed based on the artificial intelligence model to output at least one piece of promotion content.
[0057] In the present solution, the promotion content is at least one of a text type, an audio type, a video type, and an image type. When the promotion content is at least one of the text type and the image type, the target virtual image sends the promotion content. When the promotion content is at least one of the audio type and the video type, the target virtual image performs the promotion content.
[0058] The artificial intelligence model is used to generate the promotion content, which can not only produce diversified promotion content in an efficient and batch manner to greatly reduce the time cost and energy consumption of manual creation, but also accurately anchor the individualized needs and interest preferences of the target object through deep data analysis to achieve a high degree of fit between the promotion content and the target object.
[0059] The technical solution of the present disclosure embodiment acquires the target virtual image, and then publishes the promotion content in the interactive response in response to the interactive content and the interactive response meeting the promotion condition. By executing the present technical solution, the promotion content is accurately published by the target virtual image in the interactive process, which significantly improves the accuracy and efficiency of promotion.
[0060] FIG. 2 is a schematic diagram of an interactive process based on a virtual image according to an embodiment of the present disclosure. The present embodiment is a detailed description of the generation process of the target virtual image. The solution of the present embodiment can be combined with any other embodiment. The target virtual image includes a first virtual image, as shown in FIG. 2. The method includes the following steps:
[0061] S210, acquiring a first parameter; wherein the first parameter is a virtual image basic parameter.
[0062] In the present solution, the first parameter is a virtual image basic parameter, and the first parameter includes at least one of a facial feature parameter, an expression parameter, a motion parameter, a clothing and accessory parameter, an animation and rendering parameter, a personality and style parameter, and a form parameter.
[0063] In the present embodiment, the first parameter is automatically collected by responding to the input operation of the virtual image generation object on the system interface in real time.
[0064] S220, in response to receiving the first virtual image generation instruction, the artificial intelligence model executes a first virtual image generation task based on the first parameters and outputs a first virtual image corresponding to the first parameters; wherein the first virtual image includes at least one of a dynamic image and a static image.
[0065] In this scheme, the first virtual image generation instruction is used to instruct the generation of the first virtual image.
[0066] Optionally, the first virtual image generation task is used to generate the first virtual image. The artificial intelligence model executes the first virtual image generation task on the first parameters in response to receiving the first virtual image generation instruction, and generates the first virtual image corresponding to the first parameters.
[0067] The first virtual image has universality and can be used in multiple different scenarios. For example, a simple cartoon style first virtual image can be used in animation production, game development, advertising, educational content and other fields, and only needs to be adjusted and personalized according to the needs of the specific scene.
[0068] In this embodiment, the first virtual image includes at least one of a dynamic image and a static image. By adjusting the shape parameters in the first parameters, the first virtual image presents a dynamic image or a static image.
[0069] In this scheme, the type of the promotion product associated with the promotion content published by the first virtual image is limited during the generation of the first virtual image. The virtual image generation object can not only accurately define the category range of the promotion product, but also select a specific type of promotion product, realizing the customization of the promotion direction of the first virtual image.
[0070] Optionally, in the case where the adaptation promotion product type is not explicitly specified, the artificial intelligence model selects a promotion product with high matching degree based on the parameters of the first virtual image. For example, the system can automatically identify the association between animal virtual images and pet products, and preferentially recommend pet food, intelligent feeding equipment, pet health care and other promotion products with high matching degree.
[0071] When the matching degree of the selected promotion product for the first virtual image does not reach the preset threshold, the system will automatically trigger a secondary confirmation process and simultaneously start a promotion content review mechanism. If the first virtual image has a high matching degree with the promotion product, secondary confirmation is not required. For example, if the virtual image generation object creates a virtual image of a pet dog and plans to use the image to promote a chocolate product, since chocolate poses a health risk to pet dogs, there is a significant conflict in attributes and functions between the two, at which point the system will prompt the virtual image generation object to perform secondary confirmation on the selection of the promotion product. After the virtual image generation object completes the confirmation operation, the relevant promotion content will be immediately pushed to the review link to ensure the rationality and safety of the promotion content.
[0072] In this scheme, when the target virtual image is the first virtual image, the artificial intelligence model can communicate with the target object according to the input content of the target object. While communicating with the target object, the artificial intelligence model can calculate the most appropriate promotion content in real time according to all the content of the current conversation between each target object and the first virtual image, and display relevant product pictures or videos or product links. If the promotion content has an associated second virtual image, the link of the second virtual image is displayed. For example, in a conversation scenario, the target object mentions that it will rain tomorrow, but the current conversation content mentions walking to work every day. Based on the association of the double information, the artificial intelligence model will recommend an umbrella. The umbrella is more suitable for the needs of convenient storage and flexible response to changing weather in the walking commuting scenario, and can provide efficient rain protection for the target object without affecting the neatness of the dress.
[0073] The technical scheme of the embodiment of the present disclosure acquires the first parameter, and in response to receiving the first virtual image generation instruction, the artificial intelligence model executes the first virtual image generation task based on the first parameter and outputs the first virtual image corresponding to the first parameter. Through the implementation of this technical scheme, the promotion content can be accurately published in the interaction process based on the first virtual image. The ordinary interaction is combined with the promotion content based on the artificial intelligence model, the product introduction can be added in the interaction process, the rejection psychology of the target object to the product is reduced, and the conversion rate of the product is improved according to the intelligent selection of the promotion product.
[0074] FIG. 3 is a flowchart of an interaction process based on a virtual image provided by an embodiment of the present disclosure. The relationship between the present embodiment and the above-mentioned embodiments is a detailed description of the target virtual image generation process. The scheme of the present embodiment can be combined with any other embodiment. The target virtual image includes a second virtual image, as shown in FIG. 3, the method comprises:
[0075] S310, acquiring a first parameter and a second parameter; wherein the first parameter is a virtual image basic parameter, and the second parameter is a virtual image promotion parameter.
[0076] In this scheme, the first parameter is the basic parameter of the virtual avatar. The first parameter can be at least one of the following: appearance feature parameter, expression parameter, action parameter, clothing and accessory parameter, animation and rendering parameter, personality and style parameter, and form parameter.
[0077] In this embodiment, the second parameter is a parameter related to the promotion of the virtual avatar. The second parameter can be at least one of the following: appearance parameters, expression parameters, action parameters, voice parameters, personality and temperament parameters, clothing and accessory parameters, animation and rendering parameters, and form parameters.
[0078] Optionally, the first and second parameters can be automatically collected by responding to the input operations of the virtual avatar generation object on the system interface in real time.
[0079] S320. In response to receiving a second virtual avatar generation instruction, the artificial intelligence model executes the second virtual avatar generation task based on the first parameter and outputs the second virtual avatar corresponding to the first parameter; or, the artificial intelligence model executes the second virtual avatar generation task based on the first parameter and the second parameter and outputs the second virtual avatar corresponding to the first parameter and the second parameter; wherein, the second virtual avatar includes at least one of dynamic avatar and static avatar; the promotion conditions of each second virtual avatar correspond to the second parameter.
[0080] In this scheme, the second virtual avatar generation instruction is used to instruct the generation of a second virtual avatar.
[0081] Optionally, the second virtual avatar generation task is used to generate a second virtual avatar. In response to receiving a second virtual avatar generation instruction, the artificial intelligence model performs the second virtual avatar generation task on the first parameter to generate a second virtual avatar corresponding to the first parameter; or, in response to receiving a second virtual avatar generation instruction, the artificial intelligence model performs the second virtual avatar generation task on the first parameter and the second parameter to generate a second virtual avatar corresponding to the first parameter and the second parameter.
[0082] In this embodiment, the second virtual avatar is specific. The specificity of the second virtual avatar means that it has a specific purpose, scope of application, and target audience; it is typically designed and used to meet the specific needs of a particular subject in a specific context. Optionally, the second virtual avatar may be applicable to at least one of the following: specific subject-specific, specific domain application, specific functional application, specific style matching, or specific scenario.
[0083] In this context, "exclusive to a specific entity" refers to a second virtual avatar being created for a specific individual, organization, or brand. For example, a brand might generate a specific virtual avatar to promote certain products or a specific series or brand, and the promotional content displayed by such a virtual avatar will not exceed the scope of products restricted by the virtual entity it was created from; or, some virtual idol groups might create a unique second virtual avatar for each of their virtual members, and these avatars are closely bound to that member and belong to a specific entity.
[0084] In this embodiment, "specific application" refers to the second virtual avatar being designed for a specific field or industry. For example, in the field of education, some virtual teacher avatars have been developed for online teaching.
[0085] In this scheme, "specific function" means that each second virtual avatar is assigned a specific function. For example, the virtual customer service avatar is designed to provide assistance and answer questions in customer service.
[0086] In this context, "specific style matching" refers to the style of the second virtual avatar matching the brand image, cultural connotations, or specific needs of its parent company. For example, a second virtual avatar belonging to a brand that emphasizes technology tends to use simple lines, cool colors, and futuristic elements in its design to convey the brand's technological and innovative characteristics.
[0087] In this embodiment, "specific scenario" refers to the fact that the second virtual avatar is designed with specific usage scenarios in mind. For example, a second virtual avatar designed for an online game will be designed according to the game's world view, gameplay, and target audience characteristics, so that it can blend into the game scene and conform to the overall atmosphere and style of the game.
[0088] It should be understood that the above-mentioned specific style is one way of presenting the second virtual image by setting appearance parameters, which is one of the second parameters.
[0089] Optionally, the second virtual avatar is also versatile and can be used in multiple different scenarios. For example, the second virtual avatar can be used in the entertainment, advertising and marketing, and education fields.
[0090] In this embodiment, the second virtual avatar includes at least one of a dynamic avatar and a static avatar. By adjusting the morphological parameters in the second parameters, the second virtual avatar can be controlled to present either a dynamic or static avatar.
[0091] In this scheme, the first virtual image and the second virtual image can achieve dynamic transformation of morphological features by adding or removing a second parameter.
[0092] In this embodiment, both the first and second virtual avatars have the function of publishing promotional content. By default, the system configures the first virtual avatar as the core interactive subject, engaging in real-time dialogue with the target audience through preset interaction logic. The second virtual avatar, as a professional content dissemination carrier, primarily undertakes the publishing of promotional content. The usage scenarios and execution permissions of both can be flexibly switched through custom button function configurations, achieving efficient division and collaboration between interactive services and promotional operations.
[0093] In the creation of the first and second virtual characters, the relevant copyright laws and regulations were strictly followed, and there was no infringement of the copyright of others. At the same time, the infringement of derivative rights such as the portrait rights, name rights, and trademark rights of celebrities was fully avoided. Without the authorization or permission of the rights holders, the prototypes of the creation did not involve similar images of film and television characters or public figures.
[0094] Optionally, both the first and second virtual avatars will display a unique identifier when publishing promotional content to clearly indicate their product promotion attributes.
[0095] In this scheme, the promotion conditions for each second virtual avatar correspond to a second parameter. For example, if a second virtual avatar is designed based on a specific cultural element or theme, such as myths or historical figures from traditional culture, then the corresponding second parameter may also include the target audience's interest in and awareness of that cultural element. Its promotion conditions can be detected through interactive content, linking it to information about cultural exhibitions, cultural activities, and related film and literary works.
[0096] In this embodiment, when the target virtual avatar is a second virtual avatar and the target object's input content is not directly related to the promoted product, the artificial intelligence model will adopt a demand-driven response strategy. It will deeply analyze the target object's interaction content, generate interactive responses, and simultaneously utilize natural language processing and dialogue management algorithms to guide the current dialogue towards product promotion in a gradual manner, while maintaining dialogue fluency and the target object's experience, thus achieving natural and effective marketing conversion.
[0097] Specifically, when the system detects that a target user has explicitly expressed their refusal to participate in product promotion through specific input or control controls, the second virtual avatar will immediately terminate the product promotion function. It will then switch to a normal interaction mode, focusing on providing information and friendly dialogue services until the suspension period ends, at which point the product recommendation function will be restarted as appropriate based on the dialogue context. The suspension period is based on the settings of the virtual avatar's creation object; for example, a suspension period of 24 hours; or, the suspension period can be determined based on an artificial intelligence model.
[0098] In this solution, the image parameters of the first and second virtual avatars can be dynamically adjusted. For example, in lifestyle consumption scenarios, the interactive function of the virtual avatars can achieve a highly personalized presentation. When showcasing a series of clothing or cosmetics, the target audience can either select specific items for precise display or trigger a style carousel with one click to browse the entire product range. Simultaneously, the target audience can flexibly modify parameters such as body proportions and skin tone of the virtual avatar by sliding or directly inputting values, intuitively experiencing the actual effect of the promoted product under different body types and skin tones. Especially for clothing, the system will automatically and precisely define the value range of the slider based on the professional size chart entered by the merchant, ensuring that the body data adjusted by the target audience perfectly matches the actual product size, effectively enhancing the reference value for purchasing and the consumer experience.
[0099] Optionally, the second parameter also includes a promotion weight parameter, which is used to characterize the probability that the target virtual avatar will publish promotional content in the interactive response;
[0100] The promotion weight parameters must include at least the target promotion weight; the second virtual avatar is positively correlated with the target promotion weight.
[0101] In this scheme, the second parameter also includes a promotion weight parameter, which is used to characterize the probability that the target virtual character will publish promotional content in the interactive response.
[0102] The second parameter also includes an interaction weight parameter, which characterizes the probability that the target virtual avatar will only interact in the interaction response. The interaction weight parameter includes at least the target interaction weight.
[0103] Optionally, the sum of the target promotion weight and the target interaction weight is 1.
[0104] This solution allows for fine-tuning of promotion weight parameters by optimizing promotion condition settings. For example, different promotion weight parameter values can be set for different target audiences; different promotion weight parameter values can be set for different interaction scenarios.
[0105] By setting promotion weight parameters, the probability of promotional content appearing can be precisely adjusted, avoiding excessively frequent promotional content from affecting the normal interaction between the target audience and the virtual avatar. This optimizes the allocation of promotional content and improves overall promotion efficiency.
[0106] Optionally, the promotion weight parameter supports dynamic adjustment. When the target object expresses too much promotion content through input of specific content or control controls, the target promotion weight is reduced and the interaction weight parameter is increased accordingly. Alternatively, when the virtual avatar generation object needs to adjust the frequency of promotion content, the promotion weight parameter or target interaction weight value can be adjusted in real time in the data backend.
[0107] Optionally, the second parameter may also include promotional product parameters, which are associated with at least one product; these promotional product parameters are used to restrict the promotional content published by the target virtual avatar.
[0108] The target virtual avatar publishes promotional content in the interactive response, including:
[0109] In response to the triggering of the promoted product parameters, the target virtual avatar publishes promotional content related to the promoted product as defined by the promoted product parameters in the interactive response.
[0110] In this scheme, the second parameter also includes promotional product parameters, which are used to restrict the promotional content published by the target virtual avatar.
[0111] In this context, each set of promoted product parameters is associated with at least one product, meaning the relationship between the parameters and the product is exclusively bound. This exclusive binding implies that each specific set of promoted product parameters uniquely corresponds to and belongs exclusively to a particular product, forming an exclusive association mechanism. For example, when a virtual avatar is used to promote a single product, a particular type of product, a particular brand, or multiple brands and categories, its design is closely linked to the product characteristics when connected to a relatively singular advertising source. Taking a humanoid virtual avatar as an example, trademarks, logos, and product elements can be integrated into details such as clothing, accessories, and prop design to form a unified brand visual symbol, strengthening consumers' awareness and memory of the product.
[0112] Optionally, when the parameters of the promoted product meet the trigger conditions, the target virtual avatar responds to the trigger of the promoted product parameters and publishes promotional content related to the promoted product specified by the promoted product parameters in the interactive response.
[0113] By setting parameters for promoted products and limiting the promotional content associated with those products, it is helpful to increase the target audience's trust and acceptance of the promotional content, thereby increasing the click-through rate and conversion rate of the promotional content.
[0114] Optionally, the second parameter also includes pre-configured response rules associated with the product;
[0115] The target virtual avatar, based on an artificial intelligence model, outputs at least one interactive response for at least one interactive content, including:
[0116] If the second matching rate between the response rule and the interaction content is greater than or equal to the preset response rule threshold, then the artificial intelligence model is used in conjunction with the response rule to analyze and process at least one interaction content and generate at least one interaction response; otherwise, the artificial intelligence model is used to analyze and process at least one interaction content and generate at least one interaction response; wherein, the response rule includes at least the criteria for responding to interaction content pre-configured when creating the second virtual avatar.
[0117] The second matching rate is determined based on an artificial intelligence model.
[0118] In this embodiment, the response rules include at least the criteria for responding to interactive content pre-configured when creating the second virtual avatar.
[0119] In this scheme, the response rule threshold can be set by the virtual avatar generation object or obtained through inference by an artificial intelligence model. The response rule threshold can be dynamically adjusted.
[0120] Optionally, a second matching rate between at least one interactive content and the response rule is calculated based on an artificial intelligence model. When the second matching rate is greater than or equal to the response rule threshold, the artificial intelligence model is used in conjunction with the response rule to analyze and process at least one interactive content to generate at least one interactive response. When the second matching rate is less than the response rule threshold, the artificial intelligence model is used to analyze and process at least one interactive content to generate at least one interactive response.
[0121] By calculating the second matching rate between the interactive content and the response rules, the response strategy is intelligently switched based on the magnitude of the second matching rate. When the second matching rate is greater than or equal to the response rule threshold, mature response rules are prioritized to ensure professional, efficient, and standardized responses. When the second matching rate is less than the response rule threshold, more personalized content that fits the scenario is output, achieving a balance between regularity and flexibility. This allows the virtual avatar to send more appropriate responses to the interactive content of the target audience, improving user satisfaction and further increasing the click-through rate and conversion rate of promotions.
[0122] Optionally, after the interactive content and / or interactive response meet the promotion conditions, the method may also include:
[0123] The system acquires a database of products to be promoted. Based on at least one interaction and at least one interaction response in the current dialogue with the target virtual avatar, the AI model determines the third match rate corresponding to the products to be promoted and selects the product with the highest third match rate as the promoted product.
[0124] The product database for promotion covers various types of products. For example, the database includes food, beverages, clothing, shoes, hats, cosmetics, daily necessities, furniture, home appliances, automobiles, etc.
[0125] In this solution, the artificial intelligence model analyzes the interaction content and response within the current dialogue of the target virtual avatar, calculates the matching rate between the interaction content, interaction response and the product to be promoted, obtains multiple third matching rates, and selects the product with the highest third matching rate from the multiple third matching rates as the promoted product.
[0126] By identifying products to promote based on interactive content and responses, the suitability between products and target audiences is effectively improved.
[0127] Optionally, after selecting to promote a product, the following options also apply:
[0128] Determine the fourth match rate between the promoted product and the second virtual avatar;
[0129] If the fourth matching rate is greater than or equal to the preset matching threshold, the promotional content corresponding to the promoted product is obtained, and the promotional content is published through the second virtual avatar during the interaction with the target object;
[0130] If the fourth matching rate is less than the preset matching threshold, then candidate products for promotion are selected from the products to be promoted in descending order of the third matching rate. If the fourth matching rate between the candidate product and the second virtual avatar is greater than or equal to the preset matching threshold, the promotion content corresponding to the candidate product is obtained, and the promotion content is published by the second virtual avatar during the interaction with the target object.
[0131] In this scheme, the fourth matching rate between the promoted product and the second virtual avatar is calculated based on an artificial intelligence model.
[0132] The matching threshold can be set based on the virtual avatar generated object, or it can be determined based on an artificial intelligence model.
[0133] Optionally, when the fourth matching rate between the promoted product and the second virtual avatar is greater than or equal to the preset matching threshold, it indicates that there is a high compatibility between the promoted product and the second virtual avatar. In this case, the promotional content corresponding to the promoted product is obtained, and the promotional content is published through the second virtual avatar during the interaction with the target object.
[0134] In this embodiment, when the fourth matching rate between the promoted product and the second virtual avatar is less than a preset matching threshold, it indicates that the compatibility between the promoted product and the second virtual avatar is low, and the promoted product needs to be re-determined. Optionally, candidate promoted products are selected from the products to be promoted in descending order of the third matching rate. The fourth matching rate between the candidate promoted products and the second virtual avatar is calculated based on an artificial intelligence model. When the fourth matching rate between the candidate promoted products and the second virtual avatar is greater than or equal to the preset matching threshold, it indicates that there is a high compatibility between the candidate promoted products and the second virtual avatar. Then, the promotional content corresponding to the candidate promoted product is obtained, and the promotional content is published by the second virtual avatar during interaction with the target object. When the fourth matching rate between the candidate promoted products and the second virtual avatar is less than the preset matching threshold, candidate promoted products are continued to be selected from the products to be promoted until the fourth matching rate between the candidate promoted products and the second virtual avatar is greater than or equal to the preset matching threshold.
[0135] By determining the fourth match rate between the promoted product and the second virtual avatar, the second virtual avatar can more vividly and concretely showcase the product's characteristics with its unique personality and charm, thereby increasing product awareness and recognition. A high match rate between the product and the virtual avatar can generate stronger interest and positive feelings towards the product among the target audience, thus increasing interaction and engagement between the target audience and the brand.
[0136] The technical solution of this disclosure, by acquiring a second parameter, responds to receiving a second virtual avatar generation instruction, and the artificial intelligence model outputs a second virtual avatar. By executing this technical solution, promotional content can be accurately published during interaction based on a first virtual avatar. Based on the artificial intelligence model, ordinary interaction is combined with promotional content, allowing product introductions to be added during interaction, reducing the target audience's resistance to products, and intelligently selecting promotional products based on the interaction content, thus improving product conversion rates. The system significantly reduces the manpower required for product promotion through automated content production. The virtual avatar can accurately analyze user needs, generate customized product display solutions in real time for personalized inquiries, and achieve deep interaction through dynamic demonstrations, scenario simulations, and other forms, building an immersive consumer experience and helping brands achieve a dual improvement in marketing efficiency and target audience experience.
[0137] Figure 4 is a schematic diagram of the interaction process based on a virtual avatar provided in Embodiment 4 of this disclosure. The relationship between this embodiment and the above embodiments is described in detail. The solution of this embodiment can be combined with any other embodiment. As shown in Figure 4, the method includes:
[0138] S410. Obtain at least one interactive message sent by the target object in real time.
[0139] In this solution, an artificial intelligence system can collect the interactive content sent by the target object in real time.
[0140] S420. Based on the second parameter, determine the promotional content associated with at least one interactive content.
[0141] In this solution, the artificial intelligence model analyzes the second parameter and the interactive content to determine the promotional content associated with the interactive content.
[0142] S430. Based on the interactive response and promotional content, generate a target interactive response, and the second virtual avatar outputs the target interactive response, so that the second virtual avatar interacts with the interactive content.
[0143] In this embodiment, an artificial intelligence model is used to add promotional content to the interactive response, generating a target interactive response. The artificial intelligence model selects an appropriate method for inserting promotional content in different interactive scenarios. For example, promotional content can be added to a fixed position in the interactive response; alternatively, it can be added based on product-related information in the interactive response, achieving precise matching between promotional content and interactive behavior.
[0144] Optionally, the second virtual avatar outputs a target interaction response during its interaction with the target object, thus enabling the second virtual avatar to interact with the interactive content.
[0145] The technical solution of this disclosure, through acquiring interactive content and promotional content, enables the second virtual avatar to interact with the interactive content. By executing this technical solution, promotional content can be accurately published during the interaction process, significantly improving the accuracy and efficiency of promotion.
[0146] Figure 5 is a structural schematic diagram of an interactive device based on a virtual avatar provided in Embodiment 5 of this disclosure. As shown in Figure 5, the device includes:
[0147] The target virtual avatar acquisition module 510 is configured to acquire the target virtual avatar; in response to receiving at least one interactive content, the target virtual avatar outputs at least one interactive response based on an artificial intelligence model for the at least one interactive content, and the interactive response includes one or more of the following: text reply, voice reply, emoticon reply, and action reply;
[0148] The promotion content publishing module 520 responds to the interaction content and / or interaction response meeting the promotion conditions, and the target virtual character publishes promotion content in the interaction response; wherein, the promotion conditions are used to characterize the conditions under which the target virtual character publishes promotion content.
[0149] Optionally, the target virtual avatar includes a first virtual avatar, and the target virtual avatar acquisition module 510 includes:
[0150] The first parameter acquisition unit is configured to acquire the first parameter; wherein, the first parameter is the basic parameter of the virtual image;
[0151] The first virtual avatar generation unit is configured to respond to receiving a first virtual avatar generation instruction, wherein the artificial intelligence model executes the first virtual avatar generation task based on the first parameters, and outputs the first virtual avatar corresponding to the first parameters;
[0152] The first virtual image includes at least one of dynamic and static images.
[0153] Optionally, the target virtual avatar includes a second virtual avatar, and the target virtual avatar acquisition module 510 includes:
[0154] The parameter acquisition unit is configured to acquire a first parameter and a second parameter; wherein the first parameter is the basic parameter of the virtual avatar, and the second parameter is the parameter for promoting the virtual avatar;
[0155] The second virtual avatar generation unit is configured to, in response to receiving a second virtual avatar generation instruction, have the artificial intelligence model execute the second virtual avatar generation task based on the first parameters, and output the second virtual avatar corresponding to the first parameters; or,
[0156] The artificial intelligence model performs the task of generating a second virtual image based on the first parameter and the second parameter, and outputs the second virtual image corresponding to the first parameter and the second parameter.
[0157] The second virtual avatar includes at least one of dynamic and static avatars; the promotion conditions for each second virtual avatar correspond to the second parameter.
[0158] Optionally, when the target virtual avatar is a second virtual avatar, the promotional content publishing module 520 includes:
[0159] The interactive content acquisition unit is configured to acquire at least one piece of interactive content sent in real time by the target object;
[0160] The promotion content determination unit is configured to determine the promotion content associated with at least one interactive content based on the second parameter;
[0161] The target interactive response output unit is configured to generate a target interactive response based on the interactive response and promotional content. The second virtual avatar outputs the target interactive response, enabling the second virtual avatar to interact with the interactive content.
[0162] Optional promotional conditions include:
[0163] The first match rate between at least one interactive content and at least one product in the preset promotion product database is greater than or equal to the preset promotion threshold; the interaction duration with the target virtual image in the current dialogue reaches the preset interaction duration threshold; and the number of interactions with the target virtual image in the current dialogue reaches the preset number of interactions threshold.
[0164] Optionally, the second parameter also includes a promotion weight parameter, which is used to characterize the probability that the target virtual avatar will publish promotional content in the interactive response;
[0165] The promotion weight parameters must include at least the target promotion weight; the second virtual avatar is positively correlated with the target promotion weight.
[0166] Optionally, the second parameter may also include promotional product parameters, which are associated with at least one product; these promotional product parameters are used to restrict the promotional content published by the target virtual avatar.
[0167] The promotional content publishing module 520 includes:
[0168] In response to the triggering of the promoted product parameters, the target virtual avatar publishes promotional content related to the promoted product as defined by the promoted product parameters in the interactive response.
[0169] Optionally, the second parameter also includes pre-configured response rules associated with the product;
[0170] The target virtual avatar acquisition module 510 includes:
[0171] The interactive response generation unit is configured to, if the second matching rate between the response rule and the interactive content is greater than or equal to a preset response rule threshold, use an artificial intelligence model in conjunction with the response rule to analyze and process at least one interactive content and generate at least one interactive response; otherwise, use an artificial intelligence model to analyze and process at least one interactive content and generate at least one interactive response; wherein, the response rule includes at least the criteria for responding to interactive content pre-configured when creating the second virtual avatar.
[0172] Optionally, the device also includes:
[0173] The product selection module is configured to acquire a database of products to be promoted. The artificial intelligence model determines the third match rate corresponding to the products to be promoted based on at least one interaction and at least one interaction response in the current dialogue with the target virtual avatar, and selects the product with the highest third match rate as the promoted product.
[0174] Optionally, the device also includes:
[0175] The fourth matching rate determination module is configured to determine the fourth matching rate between the promoted product and the second virtual avatar;
[0176] The promotion content determination module is configured to obtain the promotion content corresponding to the promoted product if the fourth matching rate is greater than or equal to the preset matching threshold, and publish the promotion content through the second virtual avatar during the interaction with the target object;
[0177] The candidate promotion product judgment module is configured to select candidate promotion products from the products to be promoted in descending order of the third matching rate if the fourth matching rate is less than the preset matching threshold. If the fourth matching rate between the candidate promotion product and the second virtual image is greater than or equal to the preset matching threshold, the promotion content corresponding to the candidate promotion product is obtained, and the promotion content is published by the second virtual image during the interaction with the target object.
[0178] Optionally, the device also includes:
[0179] The third parameter acquisition module is configured to acquire a third parameter, which must include at least the keywords of the product to be promoted.
[0180] The promotional content output module is configured to take a third parameter as input and output at least one piece of promotional content based on an artificial intelligence model; wherein the promotional content is at least one of the following types: text, audio, video, and image.
[0181] The virtual avatar-based interactive device provided in this disclosure can execute a virtual avatar-based interactive method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of the method execution.
[0182] Figure 6 illustrates a schematic diagram of the structure of an electronic device 10 that can be used to implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0183] As shown in Figure 6, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0184] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0185] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a virtual avatar-based interaction method.
[0186] In some embodiments, a virtual avatar-based interaction method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the virtual avatar-based interaction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a virtual avatar-based interaction method by any other suitable means (e.g., by means of firmware).
[0187] Various embodiments of the systems and techniques described above 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), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transferring data and instructions to the storage system, the at least one input device, and the at least one output device.
[0188] Computer programs used to implement the methods of this disclosure may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0189] In the context of this disclosure, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0190] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device 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 provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).
[0191] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0192] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.
[0193] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.
[0194] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure. Industrial applicability
[0195] By adopting the above solution, based on a large artificial intelligence model, promotional content is accurately determined and published during the interaction between the target virtual avatar and the user, which significantly improves the accuracy and efficiency of promotion.
Claims
1. An interactive method based on virtual avatars, characterized in that, The method includes: Obtain a target virtual avatar; in response to receiving at least one piece of interactive content, the target virtual avatar outputs at least one interactive response based on an artificial intelligence model for the at least one piece of interactive content, the interactive response including one or more of text reply, voice reply, emoticon reply, and action reply; In response to the interaction content and / or interaction response meeting the promotion conditions, the target virtual avatar publishes promotion content in the interaction response; wherein, the promotion conditions are used to characterize the conditions under which the target virtual avatar publishes promotion content.
2. The method according to claim 1, characterized in that, The target virtual avatar includes a first virtual avatar, and the generation process of the target virtual avatar includes: Obtain the first parameter; wherein, the first parameter is the basic parameter of the virtual image; In response to receiving a first virtual avatar generation instruction, the artificial intelligence model executes the first virtual avatar generation task based on the first parameters and outputs the first virtual avatar corresponding to the first parameters; The first virtual image includes at least one of a dynamic image and a static image; by adjusting the morphological parameters in the first parameters, the first virtual image can be controlled to present a dynamic image or a static image.
3. The method according to claim 1 or 2, characterized in that, The target virtual avatar includes a second virtual avatar, and the generation process of the target virtual avatar includes: Obtain the first parameter and the second parameter; wherein the first parameter is the basic parameter of the virtual avatar, and the second parameter is the parameter for promoting the virtual avatar; In response to receiving a second virtual avatar generation instruction, the artificial intelligence model executes the second virtual avatar generation task based on the first parameter and outputs the second virtual avatar corresponding to the first parameter; or, The artificial intelligence model performs the second virtual image generation task based on the first parameter and the second parameter, and outputs the second virtual image corresponding to the first parameter and the second parameter. The second virtual image includes at least one of dynamic and static images; by adjusting the morphological parameters in the second parameter, the second virtual image is controlled to present a dynamic or static image; the promotion conditions for each second virtual image correspond to the second parameter.
4. The method according to any one of claims 1-3, characterized in that, When the target virtual avatar is a second virtual avatar, promotional content is published in the interactive response through the second virtual avatar, including: Retrieve at least one interactive message sent by the target object in real time; Based on the second parameter, determine the promotional content associated with the at least one interactive content; Based on the interactive response and the promotional content, a target interactive response is generated, and the second virtual avatar outputs the target interactive response, so that the second virtual avatar interacts with the interactive content.
5. The method according to any one of claims 2-4, characterized in that, By adding or removing the second parameter, the morphological characteristics of the first and second virtual images can be transformed.
6. The method according to any one of claims 1-5, characterized in that, The promotion conditions include: The first matching rate between at least one interactive content and at least one product in the preset promotion product database is greater than or equal to a preset promotion threshold, the interaction duration with the target virtual image in the current dialogue reaches a preset interaction duration threshold, and the number of interactions with the target virtual image in the current dialogue reaches a preset number of interactions threshold.
7. The method according to any one of claims 3-6, characterized in that, The second parameter also includes a promotion weight parameter, which is used to characterize the probability that the target virtual character will publish promotional content in the interactive response; The promotion weight parameters include at least the target promotion weight; the second virtual image is positively correlated with the target promotion weight.
8. The method according to any one of claims 3-7, characterized in that, The second parameter also includes promotional product parameters, which are associated with at least one product; the promotional product parameters are used to restrict the promotional content published by the target virtual avatar. The target virtual avatar publishes promotional content in the interactive response, including: In response to the triggering of the promoted product parameters, the target virtual avatar publishes promotional content associated with the promoted product specified by the promoted product parameters in the interactive response.
9. The method according to claim 8, characterized in that, When the parameters of the promoted product meet the triggering conditions, the target virtual image responds to the triggering of the promoted product parameters and publishes promotional content in the interactive response based on the promoted product parameters.
10. The method according to any one of claims 3-9, characterized in that, The second parameter also includes an interaction weight parameter, which is used to characterize the probability that the target virtual image only interacts in the interaction response; The interaction weight parameters include at least the target interaction weight.
11. The method according to any one of claims 3-10, characterized in that, The second parameter also includes pre-configured response rules associated with the product; The target virtual avatar outputs at least one interactive response based on an artificial intelligence model in response to the at least one interactive content, including: If the second matching rate between the response rule and the interaction content is greater than or equal to a preset response rule threshold, then the artificial intelligence model is used in conjunction with the response rule to analyze and process the at least one interaction content to generate at least one interaction response; otherwise, the artificial intelligence model is used to analyze and process the at least one interaction content to generate at least one interaction response; wherein, the response rule includes at least the criteria for responding to interaction content pre-configured when creating the second virtual avatar.
12. The method according to any one of claims 1-11, characterized in that, After the interactive content and / or interactive response meet the promotion conditions, the method further includes: The system acquires a database of products to be promoted. Based on at least one interaction and at least one interaction response in the current dialogue with the target virtual avatar, the artificial intelligence model determines the third matching rate corresponding to the products to be promoted and selects the product with the highest third matching rate as the promoted product.
13. The method according to claim 12, characterized in that, After selecting the product to promote, the following are also included: Determine the fourth matching rate between the promoted product and the second virtual avatar; If the fourth matching rate is greater than or equal to the preset matching threshold, then the promotional content corresponding to the promoted product is obtained, and the promotional content is published by the second virtual avatar during the interaction with the target object; If the fourth matching rate is less than the preset matching threshold, then candidate promotion products are selected from the products to be promoted in descending order of the third matching rate. If the fourth matching rate between the candidate promotion product and the second virtual image is greater than or equal to the preset matching threshold, the promotion content corresponding to the candidate promotion product is obtained, and the promotion content is published by the second virtual image during the interaction with the target object.
14. The method according to any one of claims 1-13, characterized in that, The process of generating the promotional content includes: Obtain a third parameter, which includes at least the keywords of the product to be promoted; The third parameter is used as input, and at least one piece of promotional content is output based on the artificial intelligence model; wherein, the promotional content is at least one of the following types: text, audio, video, and image.
15. The method according to claim 14, characterized in that, The third parameter also includes advertising parameters, which are at least one of advertising plot and advertising scene.
16. An interactive device based on a virtual avatar, characterized in that, The device includes: A target virtual avatar acquisition module is configured to acquire a target virtual avatar; in response to receiving at least one piece of interactive content, the target virtual avatar outputs at least one interactive response based on an artificial intelligence model for the at least one piece of interactive content, the interactive response including one or more of text reply, voice reply, emoticon reply, and action reply; The promotional content publishing module is configured to respond to the interaction content and / or interaction response reaching the promotion conditions, wherein the target virtual character publishes promotional content in the interaction response; wherein the promotion conditions are used to characterize the conditions under which the target virtual character publishes promotional content.
17. An electronic device comprising: The device includes a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and the machine-readable instructions are executed by the processor to perform the steps of the virtual avatar-based interaction method as described in any one of claims 1-15.
18. A computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the virtual avatar-based interaction method as described in any one of claims 1-15.
