Interface interaction method and device, equipment and storage medium

Abstract

The embodiment of the invention relates to an interface interaction method and device, equipment and a storage medium. The method comprises: presenting an interactive interface associated with a virtual object, the virtual object being associated with a first user, the virtual object being created based on a configuration operation of the first user; receiving a first input message of a second user through the interactive interface; and providing at least one response message generated based on the first input message, wherein the content modality of the at least one response message is determined based on the configuration operation. In this way, according to the embodiment of the invention, the content mode of the response message can be enriched based on the configuration operation of the first user in the process of creating the virtual object, and the interface interaction capability is improved.

Description

TECHNICAL FIELD

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and in particular, to an interface interaction method, apparatus, device and computer readable storage medium. BACKGROUND

[0002] With the development of computer technology, the Internet has become an important way for people to interact and obtain information. People can not only communicate information on the Internet platform, but also achieve various virtual interactions. For example, virtual objects can help users process messages in a timely manner, for example, virtual objects can autonomously generate reply content for received messages. SUMMARY

[0003] In a first aspect of the present disclosure, an interface interaction method is provided. The method comprises: presenting an interactive interface associated with a virtual object, the virtual object being associated with a first user, the virtual object being created based on a configuration operation of the first user; receiving, via the interactive interface, a first input message of a second user; and providing at least one response message generated based on the first input message, a content modality of the at least one response message being determined based on the configuration operation.

[0004] In a second aspect of the present disclosure, an apparatus for interface interaction is provided. The apparatus comprises: an interface presentation module, a message receiving module and a message response module. The interface presentation module is configured to present an interactive interface associated with a virtual object, the virtual object being associated with a first user, the virtual object being created based on a configuration operation of the first user; the message receiving module is configured to receive, via the interactive interface, a first input message of a second user; and the message response module is configured to provide at least one response message generated based on the first input message, a content modality of the at least one response message being determined based on the configuration operation.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device comprises at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. The instructions, when executed by the at least one processor, cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer readable storage medium is provided. The computer readable storage medium has stored thereon a computer program, the computer program being executable by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of the present disclosure, a computer program product is provided. The computer program product is tangibly stored in a computer storage medium and includes computer executable instructions that, when executed by a device, cause the device to perform the method of the first aspect.

[0008] It is to be understood that the content described in this Background section of this document is not intended to limit the key features or important features of embodiments of the present disclosure, nor does it limit the scope of the present disclosure. Other features of the present disclosure will be apparent from review of the following description. BRIEF DESCRIPTION OF DRAWINGS

[0009] The above and other features, aspects and advantages of embodiments of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, like reference numerals refer to like elements, wherein:

[0010] FIG. 1 A schematic diagram illustrating an example environment in which embodiments according to the present disclosure can be implemented is shown;

[0011] FIGS. 2A-2F An example interface for creating a virtual object according to some embodiments of the present disclosure is shown;

[0012] FIG. 3 An example interface for interface interaction according to some embodiments of the present disclosure is shown;

[0013] FIG. 4 A flow diagram illustrating a process for interface interaction according to some embodiments of the present disclosure is shown;

[0014] FIG. 5 A flow diagram illustrating an example process for interface interaction according to some embodiments of the present disclosure is shown;

[0015] FIG. 6 A schematic block diagram illustrating an example apparatus for interface interaction according to some embodiments of the present disclosure is shown; and

[0016] FIG. 7 A block diagram of an electronic device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0017] Embodiments of the present disclosure will be described below in greater detail with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein, but rather should be construed to encompass all alternatives and modifications falling within the scope of the present disclosure. It is to be understood that the drawings and embodiments of the present disclosure are merely for illustrative purposes and should not be construed to limit the scope of the present disclosure.

[0018] It should be noted that the headings provided in any section / subsection herein are not limitations. Various embodiments are described throughout this document and any type of embodiment can be included under any section / subsection. Furthermore, embodiments described in any section / subsection can be combined with any other embodiment described in the same section / subsection and / or a different section / subsection in any manner.

[0019] In the description of embodiments of the disclosure, the term "includes" and its derivatives, such as "including" should be understood in an open way, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions can also be included below. The terms "first", "second", etc. can refer to different or same objects. Other explicit and implicit definitions can also be included below.

[0020] In embodiments of the disclosure, data related to users, acquisition and / or use of data, etc. can be involved. These aspects all comply with corresponding laws and regulations and relevant provisions. In embodiments of the disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user is aware of and confirms. Accordingly, when implementing various embodiments of the disclosure, the type of data or information that can be involved, the scope of use, the scenario of use, etc. should be notified to the user and authorized by the user in a proper manner according to relevant laws and regulations. The specific notification and / or authorization manner can vary according to the actual situation and application scenario, and the scope of the disclosure is not limited in this regard.

[0021] In the specification and embodiments, if personal information processing is involved, it will be processed on the premise of legality (for example, obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and only within the prescribed or agreed range. Users refuse to process personal information other than the necessary information required for basic functions, which will not affect the user's use of basic functions.

[0022] As mentioned above, the virtual object can help the user to process the message in time, for example, the virtual object can autonomously generate reply content for the received message. Under the prior art, the creation and application of the virtual object mainly depend on the model, system prompt word and knowledge base, so that the virtual object can imitate the user to carry out conversation and other virtual interactions. But such a scheme has many difficulties in actual implementation and application, which makes it difficult to achieve the ideal interaction effect.

[0023] The virtual object created according to the above technology has a high requirement on the quality of the input content of the interactive user in the process of virtual interaction with the interactive user, otherwise a large amount of redundant information is easily generated, resulting in a mismatch between the response content and the input content, thereby reducing the interactive experience of the user. However, for the input content with high quality, the number of words is relatively large, and the time consumed by the virtual object to give a response content is relatively long, and the response content provided is more than the input content, and it is difficult to quickly extract the corresponding relationship between the keywords in the input content and the response content, which not only has a high interaction cost, but also has a low efficiency.

[0024] In addition, the virtual object in the prior art often uses a fixed role model, and the expression style and mode of the dialogue are single, resulting in single application scenarios and difficulty in adapting to different scenarios.

[0025] Embodiments of the present disclosure provide a scheme for interface interaction. The scheme includes: presenting an interactive interface associated with a virtual object, the virtual object being associated with a first user and being created based on a configuration operation of the first user; receiving a first input message of a second user via the interactive interface; and providing at least one response message generated based on the first input message, a content modality of the at least one response message being determined based on the configuration operation.

[0026] In this way, embodiments of the present disclosure can determine the content modality of the response message provided by the virtual object in the process of interaction with other users based on the configuration operation of the first user in the process of creating the virtual object, thereby enriching the content modality of the response message and improving the interaction capability based on the virtual object.

[0027] Various example implementations of the scheme are described in further detail below in conjunction with the accompanying drawings.

[0028] Example Environment

[0029] FIG. 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. As shown, the example environment 100 can include an electronic device 110. FIG. 1

[0030] In this example environment 100, the electronic device 110 can run an application 120 that supports interface interaction. The application 120 can be any suitable type of application for interface interaction, examples of which can include, but are not limited to, an instant messaging application, a social application, a virtual interaction application, or other suitable application. A user 140 can interact with the application 120 via the electronic device 110 and / or its attached devices.

[0031] In FIG. 1 ​In the environment 100, if the application 120 is in an active state, the electronic device 110 can present an interface 150 for supporting virtual interaction through the application 120.

[0032] In some embodiments, the electronic device 110 communicates with the server 130 to implement the provisioning of services for the application 120. The electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal including a mobile handset, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a palmtop computer, a portable gaming terminal, a VR / AR device, a Personal Communication System (PCS) device, a personal navigation device, a Personal Digital Assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an electronic book device, a game device, or any combination thereof, including an accessory or peripheral device for the foregoing, or any combination thereof. In some embodiments, the electronic device 110 can also support any type of interface to the user (such as "wearable" circuitry, etc.).

[0033] The server 130 can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and basic cloud computing services such as big data and artificial intelligence platforms. The server 130 may, for example, include a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. The server 130 can provide background services for the application 120 in the electronic device 110 that supports interface interaction.

[0034] A communication connection can be established between the server 130 and the electronic device 110. The communication connection can be established by wired or wireless means. The communication connection can include, but is not limited to, a Bluetooth connection, a mobile network connection, a Universal Serial Bus (USB) connection, a Wireless Fidelity (WiFi) connection, and the like, and embodiments of the present disclosure are not limited in this regard. In embodiments of the present disclosure, the server 130 and the electronic device 110 can implement signaling interaction through the communication connection therebetween.

[0035] It should be understood that the structure and function of the various elements in the environment 100 are described for illustrative purposes only, and do not imply any limitation on the scope of the present disclosure.

[0036] Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings.

[0037] Example Interaction

[0038] FIGS. 2A-2F Example interfaces 200A-200F are shown for creating a virtual object according to some embodiments of the present disclosure. The interfaces 200A-200F may, for example, be provided by the electronic device 110 shown. FIG. 1 As an example, the interfaces 200A-200F can be configuration interfaces for virtual objects.

[0039] In some scenarios of the present disclosure, a virtual object can be any appropriate processing entity, e.g., an agent or a bot. As an example, a virtual object can be implemented based on any appropriate machine learning model, e.g., a generative model such as a language model.

[0040] In some embodiments, a virtual object can also correspond to or be associated with an entity user. As an example, a virtual object can be created based on associated information of an entity user. Taking an entity user as a first user as an example, a virtual object can be created by the first user, e.g., the first user can create at least one virtual object according to a virtual appearance that the first user wants to present, to perform virtual interactions to achieve different virtual interaction effects and experiences. A virtual object can also be created by other users based on historical interaction records between the first user and the other users; or can be created by other users or a platform party providing virtual interaction services based on associated information provided by the first user with authorization of the first user.

[0041] As an example, a virtual object created based on the present solution can be used to perform conversational interactions with an interactive user, e.g., provide reply content to content input by the interactive user, etc.; or can perform visual interactions with the interactive user, e.g., present corresponding virtual actions based on interactive operations of the interactive user, etc. In some scenarios, a virtual object may, for example, include a virtual avatar of a user.

[0042] In some embodiments, the electronic device 110 can receive configuration operations of the user 140 via at least one of the interfaces 200A-200F to create a corresponding virtual object.

[0043] In some scenarios, the electronic device 110 can provide a creation entry for a virtual object in an interaction interface of the application 120 that can provide virtual interaction services. As an example, the interaction interface can correspond to a first user (e.g., the user 140 shown). FIG. 1 In response to triggering of the creation entry, the electronic device 110 can present the configuration interface 200A.

[0044] Reference FIG. 2A As shown in FIG. 2A, in the configuration interface 200A, the electronic device 110 can provide at least one creation option 201, e.g., “Quick creation”, “Free creation”, etc. In response to a selection of a target creation option in the at least one creation option 201, the electronic device 110 can present a plurality of configuration options in the interface 200A, to receive a configuration operation of the first user through the plurality of configuration options, so as to create the virtual object. Hereinafter, the creation process of the virtual object is exemplarily described with the triggering of “Quick creation” as an example.

[0045] In some embodiments, the electronic device 110 can present a configuration panel 210 in the configuration interface 200A, and provide a plurality of configuration items in the configuration panel 210. As an example, the plurality of configuration items can include: an “attribute” configuration item 211, a “preference” configuration item 212, a “sound” configuration item 213, and a “supplement” configuration item 214, etc.

[0046] As FIG. 2A shown, in response to the triggering of the “input” configuration item 211, the electronic device 110 can present a set of relationship options 211a in the configuration panel 210. The set of relationship options 211a can indicate a virtual relationship between the created virtual object and the interactive user.

[0047] As an example, the set of relationship options 211a can include, but is not limited to: a friend relationship, a lover relationship, an assistant relationship, etc. For example, the friend relationship can indicate that the virtual object and the interactive user can have friendly interaction in an ordinary scene; the lover relationship can indicate that the virtual object and the interactive user can have virtual interaction in a love scene; the assistant can indicate that the virtual object and the interactive user can have virtual interaction in a professional knowledge field.

[0048] As an example, in response to a selection of a target relationship option in the set of relationship options 211a, the electronic device 110 can determine a virtual relationship between the virtual object and the interactive user, and can take a first preset prompt word corresponding to the virtual relationship as at least part of the prompt information associated with the virtual object. For example, the first preset prompt word can be any one of “friend”, “lover”, “assistant”, etc.

[0049] In some embodiments, the electronic device 110 can also provide a set of characteristic options 211b in the configuration panel 210. As an example, the set of characteristic options 211b can indicate the personality characteristics and the like role characteristics corresponding to the created virtual object. For example, the set of characteristic options 211b can include, but is not limited to: romantic and free, gentle and knowledgeable, sunny and cheerful, sharp and humorous, mature and stable, proud and sharp-tongued, calm and domineering, high intelligence and cute, etc.

[0050] In response to the selection of at least one characteristic option from a set of characteristic options 211b, the electronic device 110 can determine the character characteristics such as personality traits of the created virtual object, and can also include a second preset prompt word associated with the at least one characteristic option as at least part of the prompt information associated with the virtual object. As an example, the second preset prompt word may include a descriptive word corresponding to the selected at least one characteristic option.

[0051] In some embodiments, the electronic device 110 may also provide a preview panel 220 in the configuration interface 200A. In the preview panel 220, the electronic device 110 may display visual elements 202 corresponding to the created virtual object. For example, the visual element 202 may include the virtual image, name, etc., corresponding to the virtual object. As an example, the visual element 202 may also be a visual element corresponding to the first user, such as an avatar image.

[0052] like FIG. 2A As shown, in the preview panel 220, the electronic device 110 can present a preset reference input message 221 and a preview response message 222 for the reference input message 221, wherein the preview response message 222 is associated with the configuration operation received via each configuration item in the configuration panel 210.

[0053] As an example, in response to a configuration operation on any of the options in a set of relationship options 211a and / or a set of feature options 211b, the electronic device 110 can update the preview response message 222 presented in the preview panel 220, for example, from a first preview response to a second preview response. As an example, the first preview response and the second preview response respectively indicate the reference content before and after the update corresponding to the preview response message 222. The content of the first preview response and the second preview response differs depending on the configured option. The first preview response corresponds to the preset prompt words or prompt information corresponding to each option selected before the configuration operation, and the second preview response corresponds to the preset prompt words or prompt information corresponding to each option selected after receiving the configuration operation.

[0054] In some embodiments, the electronic device 110 may also provide a first switching control 231 in the configuration interface 200A. As an example, the first switching control 231 may be configured to trigger the switching of multiple configuration items in a preset order. For example, the preset order may be a sequential order based on presentation position, from left to right or from top to bottom. FIG. 2A As shown, if the currently displayed configuration content corresponds to the "Attribute" configuration item 211, in response to the triggering of the first switching control 231, the electronic device 110 can switch the currently displayed configuration content in the configuration panel 210 to the configuration content corresponding to the "Preference" configuration item 212, for example... FIG. 2B As shown.

[0055] In some embodiments, the plurality of configuration items (e.g., configuration item 211 to configuration item 214) can be configured as triggerable options to trigger presenting configuration content corresponding to the configuration item. As an example, the electronic device 110 can also switch the currently presented configuration content in the configuration panel 210 to the configuration content corresponding to the “Preference” configuration item 212 in response to the triggering of the “Preference” configuration item 212.

[0056] With reference to FIG. 2B collectively, FIG. 2A and FIG. 2B As shown, in response to the triggering of the “Preference” configuration item 212 or the first switching control 231, the electronic device 110 can present a plurality of configuration controls corresponding to the “Preference” configuration item 212 in the configuration panel 210. As an example, the plurality of configuration controls can respectively correspond to different attributes of the virtual object. For example, the initial relationship between the virtual object and the interactive object, the expressiveness level or expressiveness style of the virtual object, the spoken or written level, the expressiveness sentence length (e.g., long or short sentences), etc.

[0057] As shown in FIG. 2B, FIG. 2B In some embodiments, the plurality of configuration controls can at least include a relationship configuration control 212a, a word number configuration control 212b, a spoken configuration control 212c, a style configuration control 212d, a format configuration control 212e, etc.

[0058] As an example, the relationship configuration control 212a can be configured to indicate the initial virtual relationship between the virtual object and the interactive user, e.g., distant (or distance), moderate, close, etc.

[0059] As an example, the word number configuration control 212b can be configured to indicate the message length or message word number sent by the virtual object, e.g., less, moderate, more, etc.

[0060] As an example, the spoken configuration control 212c can be configured to indicate the expressiveness vocabulary style of the virtual object, e.g., written, moderate, spoken, etc.

[0061] As an example, the style configuration control 212d can be configured to indicate the expressiveness tone style of the virtual object, e.g., serious, moderate, humorous, etc.

[0062] As an example, the format configuration control 212e can be configured to indicate the message output mode of the virtual object, which can be used to configure whether to present the message content of the virtual object with multiple messages, e.g., sent in one paragraph, moderate, sent in multiple paragraphs, etc.

[0063] In some embodiments, in response to receiving a preset operation (e.g., a swipe operation or a long-press operation of the first user, etc.) in the configuration panel 210, the electronic device 110 can expand the configuration panel 210 to present the configuration controls that are not presented.

[0064] FIG. 2C An expanded view of the configuration panel 210 in some embodiments is shown. As shown in FIG. 2C In the configuration panel 210, the electronic device 110 can also provide at least one modal configuration item. A configuration operation received via the at least one modal configuration item can indicate whether the virtual object is allowed to output a response message of a specified content modality.

[0065] In some embodiments, the at least one modal configuration item can include a first modal configuration item 212f and a second modal configuration item 212g. As an example, the first modal configuration item 212f can indicate whether the virtual object is allowed to output an expression content as at least part of the response message. The expression content can be an expression content in an expression database associated with the application 120, or a virtual expression associated with the visual content corresponding to the virtual object. As an example, the second modal configuration item 212g can indicate whether the virtual object is allowed to output a speech content as at least part of the response message.

[0066] In combination FIG. 2B and FIG. 2C As shown, the electronic device 110 can also provide a second switching control 232 in the configuration panel 210. As an example, the second switching control 232 can be configured to switch in an order opposite to that of the first switching control 231. For example, the first switching control 231 is configured to switch the multiple configuration items (211-214) in a left-to-right order, the second switching control 231 can be configured to switch the multiple configuration items in a right-to-left order. For example, the first switching control 231 can be presented as “next step”, and the second switching control 232 can be presented as “previous step”.

[0067] As an example, in the interface 200B shown in FIG. 2B In response to a trigger of the first switching control 231, the electronic device 110 can switch the configuration content corresponding to the “preference” configuration item 212 in the configuration panel 210 to the configuration content corresponding to the “sound” configuration item 213, as shown in the interface 200D shown in FIG. 2D In response to a trigger of the second switching control 232, the electronic device 110 can switch the current configuration content to the configuration content corresponding to the “attribute” configuration item 211, as shown in the interface 200A shown in FIG. 2A

[0068] Referring to FIG. 2D ​As shown, corresponding to the “sound” configuration item 213, the electronic device 110 can present, in the configuration panel 210, reference speech content 213a associated with the first user or the virtual object, to output a response message in a speech modality based on tone information corresponding to the reference speech content 213a as the tone information of the virtual object.

[0069] In some embodiments, in response to not obtaining the reference speech content associated with the first user, the electronic device 110 can present an audio obtaining control 233 in the configuration panel 210. For example, the audio obtaining control 233 can be presented as “start recording”. In response to triggering of the audio obtaining control 233, the electronic device 110 can obtain the reference speech content associated with the first user.

[0070] In some embodiments, in the configuration panel 210, the electronic device 110 can further provide audio description information 213b. As an example, the audio description information 213b can indicate environmental requirements for the first user to record the reference speech content, such as avoiding multi-person conversation, or avoiding obvious noise, reverberation, noise, etc. The audio description information 213b can also indicate the use of the reference speech content, such as “to be used for virtual interaction, intelligent chat”, etc.

[0071] In some embodiments, in response to receiving a confirmation operation on the obtained reference speech content 213a, the electronic device 110 can switch the audio obtaining control 233 to the first switching control 231. In response to triggering of the first switching control 231 or the “supplement” configuration item 214, the electronic device 110 can present FIG. 2E The configuration interface 200E is shown.

[0072] Reference FIG. 2E As shown, corresponding to the “supplement” configuration item 214, in the configuration panel 210, the electronic device 110 can present an input control 214a. Via the input control 214a, the electronic device 110 can obtain at least one set of input prompt words input by the first user. As an example, the at least one set of input prompt words can be used to indicate description information associated with the virtual object, such as expression style, role characteristics, etc. corresponding to the virtual object.

[0073] In some embodiments, the electronic device 110 can further provide a rewriting control 214b in the configuration panel 210. As an example, the rewriting control 214b can be configured to call a pre-trained model or algorithm to polish and rewrite the obtained at least one set of input prompt words and present in the input control 214a. For example, the rewriting control 214b can be presented as “intelligent rewriting” or the like.

[0074] In some embodiments, the electronic device 110 can combine the at least one set of input prompt words acquired via the input control 214a and / or the rewrite control 214b, with the preset prompt words determined via the configuration operations in the "property" configuration item 211, the "preference" configuration item 212, and the "sound" configuration item 213, to construct the prompt information associated with the virtual object, and further create the corresponding virtual object based on the prompt information.

[0075] As shown in FIG. 2E The electronic device 110 can further present an experience entry 234 in the configuration interface 200E. In response to the triggering of the experience entry 234, the electronic device 110 can present a conversation interface 200F associated with the virtual object. The virtual object corresponding to the conversation interface 200F is the virtual object created based on the aforementioned prompt information.

[0076] In the interface 200F, the electronic device 110 can provide an input control 241. Via the input control 241, the electronic device 110 can receive a test message 242 input by the first user. In response to receiving the test message 242, the electronic device 110 can provide a response message 243 to the test message 242 in the conversation interface 200F. The response message 243 can be generated based at least on the prompt information associated with the virtual object. Via the test message 242 and the response message 243, the first user can be presented with the conversation interaction capability of the created virtual object, so as to judge whether to create the virtual object, or whether to modify the configuration information associated with the virtual object.

[0077] In some embodiments, the electronic device 110 can further provide an edit entry 244 and a creation control 245 in the interface 200F. As an example, in response to the triggering of the edit entry 244, the electronic device 110 can again present the configuration interface 200A shown in FIG. 2A or any of the configuration interfaces shown in FIGS. 2A-2E to modify the corresponding configuration operation, so as to update the prompt information associated with the virtual object, and update the created virtual object.

[0078] As an example, in response to the triggering of the creation control 245, the electronic device 110 can create the corresponding virtual object based on the configuration operations received in the configuration interfaces 200A to 200E, for virtual interactions such as conversations with other interactive users. In this way, the creation process of a virtual object is completed.

[0079] FIG. 3 An example interface 300 of an interface interaction process according to some embodiments of the present disclosure is shown. The interface 300 may, for example, be presented by the electronic device 110. FIG. 1The electronic device 110 shown is provided. As an example, interface 300 can be an interactive interface associated with a virtual object.

[0080] In some embodiments, the virtual object can be any suitable processing entity, such as an agent or a bot. As an example, the virtual object can be implemented based on any suitable machine learning model, such as a generative model like a language model.

[0081] In some embodiments, the virtual object may be associated with a first user, and the interactive interface 300 may correspond to a second user. For example, the virtual object may be generated by the first user based on... FIGS. 2A-2F Created by the configuration operations in the process.

[0082] In some embodiments, the interactive interface 300 may be one of the interfaces of a virtual interactive application (e.g., application 120), such as a session interface corresponding to a physical user or a virtual user.

[0083] As an example, the interactive interface 300 can support multimodal interaction between a second user and a virtual object. Such interaction modalities include, but are not limited to, text interaction, audio interaction, and visual interaction. In some scenarios, the interactive interface 300 can also be referred to as a virtual interactive space or interactive container for the virtual object.

[0084] refer to FIG. 3 As shown, in the interactive interface 300, the electronic device 110 can receive input messages from a second user, such as a first input message 310, a second input message 330, or a third input message 350. In response to receiving the input message from the second user, the electronic device 110 can provide at least one response message generated based on the input message in the interactive interface 300.

[0085] In this scheme, at least one response message may include multiple content modalities, and the content modality of at least one response message is determined based on the configuration operations during the process of the first user creating the virtual object.

[0086] In some embodiments, at least one response message is generated based on a prompt message associated with the virtual object. As an example, the prompt message associated with the virtual object may be based on a prompt message sent by a first user via... FIGS. 2A-2E Determined by at least one configuration operation in the process, see reference for details. FIGS. 2A-2E The relevant descriptions in the text will not be repeated here.

[0087] Continue to refer to FIG. 3As shown, as an example, for the first input message 310, the electronic device 110 can provide a first response message 321 and a second response message 322, which can both be text content. As an example, for the second input message 330, the electronic device 110 can provide a third response message 341, a fourth response message 342, and a fifth response message 343. The third response message 341 can be emoji content, the fourth response message 342 can be voice content, and the fifth response message 343 can be text content. For the third input message 350, the electronic device 110 can provide a sixth response message 360, which can be emoji content.

[0088] It should be noted that in the present scheme, the input messages (e.g., input messages 310, 330, 350) of the second user received by the electronic device 110 can be multi-modal content, such as at least one of text content, voice content, emoji content, image content, video content, etc.

[0089] In this way, embodiments of the present disclosure can determine the content modalities of the response messages provided by the virtual object in the interaction with other users based on the configuration operation of the first user in the process of creating the virtual object, thereby enriching the content modalities of the response messages and improving the interaction capability based on the virtual object.

[0090] In some embodiments, taking the first input message 310 as an example, the process of providing at least one response message by the electronic device 110 includes: first providing a first response message 321 generated based on the first input message 310; and then generating a supplementary message of the first response message 321 based on the first input message 310 and the first response message 321 as a second response message 322 and presenting it in the interaction interface 300. As an example, the first response message 321 can be generated based on the first input message 310, or can be generated based on the first input message 310 and the historical conversation messages of the second user with the virtual object.

[0091] In some embodiments, in the multiple response messages for the same input message, the content modalities of different response messages are independent of each other, i.e., for the content modality of each response message, it is judged independently by the electronic device 110 or the model associated with the virtual object. For example, for the first input message 310, the content modalities of the first response message 321 and the second response message 322 corresponding thereto can be the same; and for the second input message 330, the content modalities of the third response message 341, the fourth response message 342, and the fifth response message 343 corresponding thereto are all different.

[0092] In some embodiments, in the case that the at least one response message corresponds to two or more response messages, e.g., responses to the first input message 310 or the second input message 330, the electronic device 110 can present a message placeholder element corresponding to the next response message in the interactive interface 300 before generating the next response message after presenting the previous response message; and then update the message placeholder element to present the generated next response message after generating the next response message.

[0093] In some embodiments, the electronic device 110 can determine whether to continue generating the next response message based on whether the generated at least one response message meets a termination condition. In response to the current at least one response message meeting the termination condition, the electronic device 110 can determine not to continue generating the response message; otherwise, continue generating the next response message.

[0094] As an example, the termination condition can include at least one of the following: the current at least one response message includes reply content of any inquiry content in the input message of the second user; the number of the at least one response message reaches a threshold (e.g., a preset maximum of 3 or 5 replies for an input message, etc.); the current last response message includes interactive guidance content. As an example, the interactive guidance content can include inquiry content (e.g., “Which option do you prefer?” “Are you satisfied with my performance?” etc.), at least one interactive option (e.g., a like option, a share option, etc.), etc.

[0095] In this way, the message placeholder element can intuitively present the second user that the at least one response message has not been presented completely, thereby effectively avoiding the second user mistakenly thinking that the response message provided by the virtual object is incomplete due to not presenting the subsequent response message in time, and thereby improving the interaction ability based on the virtual object and ensuring the interactive experience.

[0096] FIG. 4 A flowchart of a message processing process of interface interaction is shown according to some embodiments of the present disclosure. Referring to FIG. 4 As shown, after receiving the user input 401 of the second user, the electronic device 110 can combine the historical conversation 402 between the second user and the virtual object to jointly execute the security policy 403 to perform security review on the user input 401, and pass the message meeting the security policy 403 as the input message of the second user.

[0097] The electronic device 110 can determine, based on the configuration operation of the first user in the process of creating the virtual object, character setting information corresponding to the virtual object, i.e., the virtual character setting 404. As an example, the electronic device 110 can determine, based on the configuration operation of the first user, configuration information and prompt information for the virtual object in terms of attributes 404a, styles 404b, voices 404c, supplements 404d, etc., and determine the virtual character setting 404 associated with the virtual object based on the configuration information and the prompt information.

[0098] In some embodiments, the electronic device 110 can perform, based on the virtual character setting 404 of the virtual object, a processing process 405 in combination with the input message that complies with the safety policy 403, to rewrite the input message and determine the degree of association between the second user and the virtual object, e.g., the degree of association of the virtual object to the second user. As an example, the degree of association can represent the degree of friendliness expressed by the second user to the virtual object.

[0099] As an example, the rewriting of the input message in the processing process 405 is to correct the misspelling, grammatical error, incorrect punctuation, etc. in the user input 401 without changing the original intention of the user input 401, so as to avoid the understanding deviation of the subsequent algorithm or model in the processing process. After the user input 401 and the historical conversation 402 are executed in the processing process 405, the rewritten user input and the historical conversation 406 can be obtained.

[0100] As an example, for the degree of association determination in the processing process 405, the electronic device 110 can perform semantic analysis on the user input 401 to identify the current expression state of the second user, feedback information (e.g., the degree of recognition of the virtual object, etc.). The semantic analysis is performed on the historical conversation 402 to identify the current degree of association of the virtual object to the second user.

[0101] In some embodiments, the electronic device 110 can also combine the current expression state and feedback information of the second user with the virtual character setting 404 to determine the degree of association increment of the virtual object to the current conversation. For example, when the input message of the second user indicates positive feedback to the virtual object, the corresponding degree of association increment is positive. Conversely, when the input message of the second user indicates negative feedback to the virtual object, the corresponding degree of association increment is negative.

[0102] The electronic device 110 can update the degree of association of the virtual object to the second user after receiving the user input 401 according to the degree of association increment obtained based on the input message and the current degree of association.

[0103] In some embodiments, the electronic device 110 can analyze the state feature and reply strategy of the virtual object for the input message based on the identified user expression state and feedback information, in combination with the current degree of association of the second user with the virtual object and the degree of association increment, to obtain the degree of association information and the reply suggestion 407 corresponding to the virtual object.

[0104] As an example, the electronic device 110 can divide the relationship between the virtual object and the second user into stages by taking the degree of association increment and the current degree of association as the basis, and configure differentiated interaction rules for different stages to assist in quickly determining the reply strategy of the virtual object for the user input 401. For example, taking the current degree of association as the horizontal coordinate (for example, the change trend from “distant” to “intimate”), and taking the degree of association increment as the vertical coordinate, a “state-feedback” cross table between the second user and the virtual object can be configured to assist in determining the reply strategy of the virtual object for the user input 401.

[0105] In some embodiments, the electronic device 110 can also combine the degree of association information and the reply suggestion 407 with the virtual persona 404 of the virtual object to integrate the prompt information 408 required to generate a response message as the reply strategy of the virtual object for the user input 401.

[0106] In this way, the embodiments of the present disclosure can realize differentiated interaction experiences when the same user faces different virtual objects and the same virtual object faces different users through the closed-loop logic of “expression state recognition-degree of association calculation-relationship matching-reply strategy generation”, not only giving the virtual object the expression state perception ability, but also realizing the cross influence of the virtual persona and the degree of association.

[0107] In some embodiments, the electronic device 110 can trigger the update of the current degree of association of the virtual object to the second user based on the current last input message and / or at least one generated response message after generating the last response message each time, that is, updating the degree of association between the virtual object and the second user.

[0108] Continuing to refer to FIG. 4 As shown, the electronic device 110 can provide the rewritten user input and the historical conversation 406 to the agent 410 associated with the virtual object in combination with the prompt information 408. As an example, the agent 410 can be associated with a pre-trained machine learning model, such as a generative model of a language model. For example, the agent 410 can be trained based on a multi-model superposition training strategy 410a.

[0109] In some embodiments, the agent 410 can output a model reply for the user input 401. As an example, the model reply can include text content corresponding to the first response message and indication information about whether to generate additional response messages.

[0110] In some embodiments, after outputting the model reply, the agent 410 can trigger the first judgment condition 420 to determine whether to trigger the multi-modal response. As an example, if the multi-modal response does not need to be triggered, the electronic device 110 can directly generate a corresponding text reply 430a based on the text content in the model reply.

[0111] As an example, if the multi-modal response needs to be triggered, and the configuration operation associated with the virtual object includes selection of expression content, the electronic device 110 can perform expression resource retrieval 431 from an expression database associated with the application 120 based on the text content in the model reply to find expression content matching the text content, and generate a corresponding expression reply 430b. As an example, the expression resources in the expression database associated with the application 120 can include virtual expressions associated with visual content corresponding to the virtual object.

[0112] As an example, if the multi-modal response needs to be triggered, and the configuration operation associated with the virtual object includes selection of voice content, the electronic device 110 can identify the text content 432 based on the text content in the model reply, and trigger a TTS (Text-to-Speech) module 433 to convert the text content 432 into voice content to obtain a voice reply 430c.

[0113] After obtaining any one of the text reply 430a, the expression reply 430b, or the voice reply 430c, the electronic device 110 can trigger the second judgment condition 440 to determine whether to continue to generate the next response message. As an example, the electronic device 110 can determine whether to continue to generate the next response message based on the current reply number (the number of response messages for the current input message), the content of the currently generated response message, the user input 401, and the like.

[0114] As an example, the electronic device 110 can determine that the first response message can be input as a response reply 450 in the case where additional response messages do not need to be generated based on the indication information in the model reply about whether to generate additional response messages.

[0115] In response to a need to generate an additional response message, the electronic device 110 can continue to execute to trigger the next reply reference information and provide a message placeholder element in the interactive interface. As an example, the electronic device 110 can generate the next reply reference information 460 based on the user input 401 and the currently generated response content.

[0116] In some embodiments, the first response message can be independent of the knowledge information or the memory information associated with the virtual object. Then in a case where it is determined that a next response message needs to be generated, the agent 410 can trigger the generation of the next reply reference information 460 based on the knowledge information and / or the memory information associated with the virtual object, to ensure the content accuracy and content richness of the next reply reference information 460.

[0117] In some embodiments, in response to determining that a next response message needs to be generated, i.e., determining that the third determination condition 470 has a determination result of using a RAG (Retrieval-Augmented Generation) technology, the electronic device 110 can further trigger the execution of RAG retrieval 472 from a platform knowledge base 471 associated with the application 120 to obtain at least one retrieval result, and then execute result sorting 473 to sort the obtained retrieval results according to a preset rule, and generate the next reply reference information 460 based on the sorting result, the user input 401 and the previous response message.

[0118] In some embodiments, in response to determining that a next response message needs to be generated, the electronic device 110 can further determine that the fourth determination condition 480 has a determination result of using memory information, so as to trigger the execution of memory retrieval 482 from a long-term memory database 481 associated with the virtual object to obtain a memory retrieval result associated with the user input 401. Then the electronic device 110 can further apply the memory retrieval result to generate the next reply reference information 460, so as to sufficiently improve the content richness and content accuracy of the next reply reference information 460.

[0119] After obtaining the next reply reference information 460, the electronic device 110 can input the next reply reference information 460 into the agent 410 to obtain a corresponding model reply, and continue to execute the first determination condition 420 to determine the content modality of the next response message, so as to generate a corresponding response message and execute the second determination condition 440 again. In this way, until there is no need to generate a next response message.

[0120] In this way, the embodiments of the present disclosure can determine the content modal of the response message provided by the virtual object in the interaction with other users based on the configuration operation of the first user in the process of creating the virtual object, thereby enriching the content modal of the response message and improving the interaction capability based on the virtual object.

[0121] Example Process

[0122] FIG. 5 A flowchart illustrating an example process 500 of interface interaction is shown in accordance with some embodiments of the present disclosure. Process 500 can be implemented at electronic device 110. Process 500 is described below with reference to FIG. 1 FIG. 1.

[0123] As shown in FIG. 5, at block 510, electronic device 110 presents an interaction interface associated with a virtual object, the virtual object being associated with a first user and the virtual object being created based on a configuration operation of the first user. FIG. 5

[0124] At block 520, electronic device 110 receives, via the interaction interface, a first input message of a second user.

[0125] At block 530, electronic device 110 provides at least one response message generated based on the first input message, a content modal of the at least one response message being determined based on the configuration operation.

[0126] In this way, the embodiments of the present disclosure can determine the content modal of the response message provided by the virtual object in the interaction with other users based on the configuration operation of the first user in the process of creating the virtual object, thereby enriching the content modal of the response message and improving the interaction capability based on the virtual object.

[0127] In some embodiments, the at least one response message is generated based on prompt information associated with the virtual object, and the prompt information is determined based on the following process: presenting a configuration interface of the virtual object to the first user; receiving the configuration operation of the first user via the configuration interface; and constructing the prompt information based on a preset prompt word corresponding to at least one configuration item indicated by the configuration operation.

[0128] In this way, the embodiments of the present disclosure can construct the prompt information associated with the virtual object based on the preset prompt word corresponding to the configuration item indicated by the configuration operation, as the virtual persona of the virtual object, and generate the response message accordingly, thereby effectively ensuring the consistency of the response message with the virtual persona of the virtual object, ensuring the accuracy of the response message, and improving the interaction capability based on the virtual object.

[0129] ​In some embodiments, receiving the configuration operation of the first user via the configuration interface includes: presenting, in the configuration interface, a plurality of configuration controls corresponding to different attributes; and receiving the configuration operation of the first user via the plurality of configuration controls.

[0130] In this way, the embodiments of the present disclosure can receive configuration operations of the virtual object based on the plurality of configuration controls corresponding to different attributes, thereby configuring a plurality of different attributes of the virtual object, effectively enriching the attribute information of the virtual object, ensuring the richness of the character corresponding to the virtual object, improving the personality attribute of the virtual object, and further improving the interaction capability based on the virtual object.

[0131] In some embodiments, the plurality of configuration controls includes at least one of: a first configuration control for configuring a virtual relationship between the virtual object and the interactive user; a second configuration control for configuring a role characteristic of the virtual object; a third configuration control for configuring a message length sent by the virtual object; and a fourth configuration control for configuring an expression style of the virtual object.

[0132] In this way, the embodiments of the present disclosure can configure the virtual object from the role characteristic, the expression style, the message length sent, and the virtual relationship with the interactive user, thereby effectively enriching the attribute information of the virtual object, ensuring the richness of the character corresponding to the virtual object, improving the personality attribute of the virtual object, and further improving the interaction capability based on the virtual object.

[0133] In some embodiments, constructing the prompt information based on the preset prompt word corresponding to the at least one configuration item indicated by the configuration operation includes: presenting an input control in the configuration interface; and constructing the prompt information based on the preset prompt word and an input prompt word obtained via the input control.

[0134] In this way, the embodiments of the present disclosure can obtain an input prompt word via an input control, and combine it with a preset prompt word corresponding to a configuration item to construct prompt information associated with a virtual object. Thus, the attribute of the virtual object can be further supplemented and enriched by the input prompt word, thereby further improving the richness of the character corresponding to the virtual object, improving the personality attribute of the virtual object, and further improving the interaction capability based on the virtual object.

[0135] In some embodiments, the configuration interface includes a preset area, the preset area presents a preset second input message and a first preview response to the second input message, and the configuration interface is further configured to: in response to the configuration operation, update the first preview response in the preset area to a second preview response.

[0136] In this way, the embodiment of the present disclosure can update the preview response presented by the virtual object in real time as the configuration operation changes in the process of creating the virtual object, thereby improving the visualization degree of the response effect of the virtual object corresponding to the configuration operation, realizing the visualization of the interactive effect corresponding to the configuration operation, thereby facilitating the accuracy of the configuration information corresponding to the configuration operation, improving the interaction ability in the process of creating the virtual object, and taking into account the creation accuracy of the virtual object.

[0137] In some embodiments, the configuration operation further indicates a message output mode of the virtual object, the message output mode indicating whether to present the response content of the virtual object by using multiple messages.

[0138] In this way, the embodiment of the present disclosure can configure the message output mode of the virtual object to indicate whether to present the response content by using multiple messages, so that the expression style of the virtual object can be presented by different message output modes, further improving the interaction ability based on the virtual object.

[0139] In some embodiments, the configuration operation further indicates whether the virtual object allows to output a response message of a specified content modality, the specified content modality including at least one of the following: expression content, voice content.

[0140] In this way, the embodiment of the present disclosure can configure whether the virtual object runs to output expression content and voice content in the process of creating the virtual object, so as to enrich the content modality of the response message output by the virtual object, and improve the interaction ability of the virtual object and the interaction experience with the virtual object.

[0141] In some embodiments, providing at least one response message generated based on the first input message includes: providing a first response message generated based on the first input message; and after providing the first response message, providing a second response message generated based on the first input message and the first response message.

[0142] In this way, the embodiment of the present disclosure can generate a corresponding next response message based on the provided previous response message in combination with the input message, thereby ensuring the association and continuity between multiple response messages, and effectively avoiding excessive repetition of the content of different response messages, improving the conciseness of multiple response messages, and improving the interaction ability of the virtual object.

[0143] In some embodiments, the first response message corresponds to a first content modality, and the second response message corresponds to a second content modality, the second content modality being independent of the first content modality.

[0144] In this way, the embodiments of the present disclosure can independently determine the content modalities of each response message when providing the response message, thereby ensuring the content modality independence between multiple response messages, ensuring the richness of the content modalities of the multiple response messages, and improving the interaction ability of the virtual object.

[0145] In some embodiments, the at least one response message is generated based on a process including: generating a first response message based on the first input message, the first response message being independent of knowledge information or memory information associated with the virtual object; in response to determining that an additional response message needs to be generated, determining reference information associated with the first input message based on the knowledge information and / or the memory information; and generating a second response message based on the reference information and the first response message.

[0146] In this way, the embodiments of the present disclosure can quickly generate a first response message based on the input message of the user independently of the knowledge information or the memory information associated with the virtual object, thereby ensuring the provision efficiency of the first response message; then generate a second response message based on the knowledge information and / or the memory information associated with the virtual object in combination with the first response message, thereby ensuring the content richness and the content accuracy of the second response message, and ensuring the content association and the content continuity between the second response message and the first response message.

[0147] In some embodiments, the model associated with the virtual object is configured to: output a model reply for the first input message, the model reply including text content corresponding to the first response message and indication information about whether an additional response message needs to be generated.

[0148] In this way, the embodiments of the present disclosure can quickly obtain the text content corresponding to the first response message and the indication information about whether an additional response message needs to be generated based on the model associated with the virtual object, thereby ensuring the generation efficiency and the content accuracy of the first response message, and quickly determining whether a subsequent additional response message needs to be generated, thereby improving the response efficiency of the virtual object.

[0149] In some embodiments, providing the second response message generated based on the first input message and the first response message includes: presenting a message placeholder element in the interaction interface before the second response message is generated; and in response to the second response message being generated, updating the message placeholder element to present the second response message.

[0150] In this way, the embodiment of the present disclosure can present the message placeholder element first before the subsequent response message is generated in the scenario of outputting multiple response messages, and then present the subsequent response message by updating the message placeholder element after the subsequent response message is generated. Thus, the present solution can intuitively present the interactive user that at least one response message has not been presented by the message placeholder element, so as to effectively avoid the interactive user from mistakenly believing that the response message provided by the virtual object is incomplete due to the failure to timely present the subsequent response message, thereby improving the interaction ability based on the virtual object and ensuring the interactive experience.

[0151] In some embodiments, the at least one response message is generated based on the following process: determining the association degree of the second user with the virtual object, the association degree being determined based on historical interaction content of the second user and the virtual object; and generating the at least one response message based on the association degree and the first input message.

[0152] In this way, the embodiment of the present disclosure can generate a response message for the second user input message in combination with the association degree between the second user and the virtual object, effectively ensuring the adaptability of the response message to the association degree of the second user and the virtual object, thereby improving the authenticity of the conversation process, ensuring the accuracy and personification of the response message, and improving the interaction ability based on the virtual object.

[0153] In some embodiments, the process 500 further includes that the electronic device 110 triggers updating of the association degree based on the first input message and / or the at least one response message.

[0154] In this way, the embodiment of the present disclosure can update the association degree between the second user and the virtual object in real time in the case of receiving an input message or generating a corresponding message, thereby improving the authenticity of the subsequent response process and the personification of the response message, and improving the interaction ability based on the virtual object.

[0155] Example Devices and Equipment

[0156] Embodiments of the present disclosure also provide a corresponding device for implementing the above method or process. FIG. 6 A schematic structural block diagram of an example device 600 for interface interaction according to certain embodiments of the present disclosure is shown. The device 600 can be implemented as or included in the electronic device 110. Various modules / components in the device 600 can be implemented by hardware, software, firmware, or any combination thereof.

[0157] As FIG. 6As shown, the apparatus 600 includes an interface presenting module 610, a message receiving module 620, and a message responding module 630. The interface presenting module 610 is configured to present an interactive interface associated with a virtual object, the virtual object being associated with a first user and being created based on a configuration operation of the first user; the message receiving module 620 is configured to receive, via the interactive interface, a first input message of a second user; and the message responding module 630 is configured to provide at least one response message generated based on the first input message, a content modality of the at least one response message being determined based on the configuration operation.

[0158] In some embodiments, the at least one response message is generated based on prompt information associated with the virtual object, and the prompt information is determined based on a process including: presenting, to the first user, a configuration interface of the virtual object; receiving, via the configuration interface, the configuration operation of the first user; and constructing the prompt information based on a preset prompt word corresponding to at least one configuration item indicated by the configuration operation.

[0159] In some embodiments, receiving, via the configuration interface, the configuration operation of the first user includes: presenting, in the configuration interface, a plurality of configuration controls corresponding to different attributes; and receiving, via the plurality of configuration controls, the configuration operation of the first user.

[0160] In some embodiments, the plurality of configuration controls includes at least one of: a first configuration control for configuring a virtual relationship between the virtual object and an interactive user; a second configuration control for configuring a role characteristic of the virtual object; a third configuration control for configuring a message length sent by the virtual object; and a fourth configuration control for configuring an expression style of the virtual object.

[0161] In some embodiments, constructing the prompt information based on a preset prompt word corresponding to at least one configuration item indicated by the configuration operation includes: presenting, in the configuration interface, an input control; and constructing the prompt information based on the preset prompt word and an input prompt word obtained via the input control.

[0162] In some embodiments, the configuration interface includes a preset area presenting a preset second input message and a first preview response to the second input message, and the configuration interface is further configured to update, in response to the configuration operation, the first preview response in the preset area to a second preview response.

[0163] In some embodiments, the configuration operation further indicates a message output mode of the virtual object, the message output mode indicating whether to present response content of the virtual object with multiple messages.

[0164] In some embodiments, the configuration operation further indicates whether the virtual object allows output of a response message specifying a content modality, the content modality including at least one of: expression content, voice content.

[0165] In some embodiments, the message response module is configured to: provide a first response message generated based on the first input message; and after providing the first response message, provide a second response message generated based on the first input message and the first response message.

[0166] In some embodiments, the first response message corresponds to a first content modality, and the second response message corresponds to a second content modality, the second content modality being independent of the first content modality.

[0167] In some embodiments, the at least one response message is generated based on a process including: generating a first response message based on the first input message, the first response message being independent of knowledge information or memory information associated with the virtual object; in response to determining that an additional response message needs to be generated, determining reference information associated with the first input message based on the knowledge information and / or the memory information; and generating a second response message based on the reference information and the first response message.

[0168] In some embodiments, the model associated with the virtual object is configured to: output a model reply for the first input message, the model reply including text content corresponding to the first response message and indication information about whether an additional response message needs to be generated.

[0169] In some embodiments, providing the second response message generated based on the first input message and the first response message includes: before the second response message is generated, presenting a message placeholder element in the interactive interface; and in response to the second response message being generated, updating the message placeholder element to present the second response message.

[0170] In some embodiments, the at least one response message is generated based on a process including: determining an association degree of the second user with the virtual object, the association degree being determined based on historical interaction content of the second user and the virtual object; and generating the at least one response message based on the association degree and the first input message.

[0171] In some embodiments, the apparatus 600 further includes a module that performs a process of triggering an update of the association degree based on the first input message and / or the at least one response message.

[0172] As FIG. 7As shown, the electronic device 700 is in the form of a general electronic device. Components of the electronic device 700 can include, but are not limited to, at least one processor 710 or processing unit, a memory 720, a storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. The processor 710 can be a real or virtual processor and is capable of performing various processing according to programs stored in the memory 720. In a multi-processor system, multiple processors perform computer-executable instructions in parallel to improve parallel processing capability of the electronic device 700.

[0173] The electronic device 700 typically includes a plurality of computer storage media. Such media can be any available media that is accessible by the electronic device 700 and includes both volatile and non-volatile media, removable and non-removable media. The memory 720 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 730 can be a removable or non-removable media and can include a machine-readable medium, such as a flash drive, a magnetic disk, or any other medium that can be used to store information and / or data and that can be accessed by the electronic device 700.

[0174] The electronic device 700 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 7 disk drives for reading from or writing to a removable, non- volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable, non-volatile optical disk (e.g., a CD-ROM). In these instances, each drive can be connected to the bus (not shown) by one or more data media interfaces. The memory 720 can include a computer program product 725 having one or more program modules configured to carry out the various methods or actions of the various embodiments of the present disclosure.

[0175] The communication unit 740 enables communication with other electronic devices over communication media. Additionally, functionality of the components of the electronic device 700 can be implemented in a single computing cluster or a plurality of computer machines that are capable of communicating over a communication connection. As such, the electronic device 700 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network nodes in a distributed computing environment.

[0176] Input device 750 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. Output device 760 can be one or more output devices, such as a display, a speaker, a printer, etc. Electronic device 700 can also communicate with one or more external devices (not shown) such as a storage device, a display device, etc. through communication unit 740, as desired, in order to communicate with one or more devices that enable a user to interact with electronic device 700, or to communicate with any device (e.g., a network card, a modem, etc.) that enables electronic device 700 to communicate with one or more other electronic devices. Such communication can be carried out via an input / output (I / O) interface (not shown).

[0177] According to an example implementation of the present disclosure, a computer readable storage medium is provided having computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to implement the method described above. According to an example implementation of the present disclosure, a computer program product is also provided that is tangibly stored on a non-transitory computer readable medium and includes computer executable instructions, where the computer executable instructions are executed by a processor to implement the method described above.

[0178] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0179] These computer readable program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions can also be stored in a computer readable storage medium that can include a non-transitory computer readable storage medium. The instructions stored on the computer readable storage medium can be used to program a computer, a programmable data processing apparatus, and / or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable data processing apparatus implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0180] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0181] The computer program product of the present disclosure can be a computer program product, which is a machine-readable medium (media) having instances of the software embodied thereon, such as computer software, firmware, wireless application protocol (WAP), middleware or microcode. For example, a computer program product can be a floppy disk, a CD-ROM, a DVD, a Blu-ray Disc™, a flash drive, a memory stick, a magnetic tape, or a hard disk drive. The machine-readable medium can be a single medium, or multiple media, of the same or different type. The computer program product can be one or more computer program components embodied in medium and / or transmission signals. The computer program product can have one or more computer readable and / or computer executable components embodied in medium and / or transmission signals. The computer program product can be one or more computer readable and / or computer executable components embodied in medium and / or transmission signals. The computer program product can also be at least one or combination of controller(s) with associated computer program component(s), the computer program component(s) being an example of computer program product.

[0182] The foregoing description of implementations has been presented for the purposes of illustration and description. It is not intended to be exhaustive or to limit the implementations to the precise form disclosed. Many modifications and variations are possible in light of the above teaching. It is intended that the scope of the implementations be limited not by this detailed description, but rather by the claims appended hereto.

Claims

1. A user interface interaction method, comprising: An interactive interface is presented that is associated with a virtual object, which is associated with a first user and is created based on the configuration operations of the first user; The first input message from the second user is received via the interactive interface. as well as Provide at least one response message generated based on the first input message, wherein the content modality of the at least one response message is determined based on the configuration operation.

2. The method according to claim 1, wherein, The at least one response message is generated based on a prompt message associated with the virtual object, and the prompt message is determined based on the following process: Present the configuration interface of the virtual object to the first user; The configuration operation of the first user is received via the configuration interface; as well as The prompt information is constructed based on a preset prompt word corresponding to at least one configuration item indicated by the configuration operation.

3. The method according to claim 2, wherein, The step of receiving the configuration operation from the first user via the configuration interface includes: The configuration interface presents multiple configuration controls corresponding to different attributes; and The configuration operation of the first user is received via the multiple configuration controls.

4. The method according to claim 3, wherein, The plurality of configuration controls includes at least one of the following: The first configuration control is used to configure the virtual relationship between the virtual object and the interactive user; The second configuration control is used to configure the role characteristics of the virtual object; The third configuration control is used to configure the message length sent by the virtual object; The fourth configuration control is used to configure the expression style of the virtual object.

5. The method according to claim 2, wherein, The step of constructing the prompt information based on preset prompt words corresponding to at least one configuration item indicated by the configuration operation includes: The configuration interface displays input controls; and The prompt information is constructed based on the preset prompt words and the input prompt words obtained through the input control.

6. The method according to claim 2, wherein, The configuration interface includes a preset area, which displays a preset second input message and a first preview response to the second input message. Furthermore, the configuration interface is configured to: In response to the configuration operation, the first preview response in the preset area is updated to the second preview response.

7. The method according to claim 1, wherein, The configuration operation also indicates the message output mode of the virtual object, which indicates whether to use multiple messages to present the response content of the virtual object.

8. The method according to claim 1, wherein, The configuration operation also indicates whether the virtual object is allowed to output response messages of a specified content modality, which includes at least one of the following: emoticon content and voice content.

9. The method according to claim 1, wherein, Providing at least one response message generated based on the first input message includes: Provide a first response message generated based on the first input message; and After providing the first response message, a second response message generated based on the first input message and the first response message is provided.

10. The method according to claim 9, wherein, The first response message corresponds to a first content modality, and the second response message corresponds to a second content modality, which is independent of the first content modality.

11. The method according to claim 9, wherein, The at least one response message is generated based on the following process: Based on the first input message, the first response message is generated, and the first response message is independent of the knowledge information or memory information associated with the virtual object; In response to determining that an additional response message needs to be generated, reference information associated with the first input message is determined based on the knowledge information and / or the memory information; as well as Based on the reference information and the first response message, the second response message is generated.

12. The method according to claim 11, wherein, The model associated with the virtual object is configured as follows: Output a model response to the first input message, the model response including text content corresponding to the first response message and indication information about whether the additional response message needs to be generated.

13. The method according to claim 9, wherein, The provision of the second response message generated based on the first input message and the first response message includes: Before the second response message is generated, a message placeholder element is presented in the interactive interface; and In response to the generation of the second message, the message placeholder element is updated to present the second response message.

14. The method according to claim 1, wherein, The at least one response message is generated based on the following process: The degree of association between the second user and the virtual object is determined based on the historical interaction content between the second user and the virtual object; as well as Based on the degree of association and the first input message, the at least one response message is generated.

15. The method of claim 14, further comprising: Trigger an update to the association level based on the first input message and / or the at least one response message.

16. A device for interface interaction, comprising: The interface presentation module is configured to present an interactive interface associated with a virtual object, which is associated with a first user and is created based on the configuration operations of the first user; The message receiving module is configured to receive a first input message from a second user via the interactive interface; as well as The message response module is configured to provide at least one response message generated based on the first input message, wherein the content modality of the at least one response message is determined based on the configuration operation.

17. An electronic device comprising: At least one processor; as well as At least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method according to any one of claims 1 to 15 when executed by the at least one processor.

18. A computer-readable storage medium having stored thereon computer-executable instructions that can be executed by a processor to implement the method according to any one of claims 1 to 15.

19. A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method according to any one of claims 1 to 15.

Images