Message interaction method and device, equipment and storage medium

Abstract

The embodiment of the invention relates to a message interaction method and device, equipment and a storage medium. The method provided by the invention comprises the following steps: receiving a first message input by a user in an interactive interface with a virtual object; presenting a second message generated by the virtual object based on the first message; and providing a first expression associated with the second message, wherein the first expression is determined from a preset first expression library based on the second message. In this way, according to the embodiment of the invention, the virtual object can be supported to reply the message by calling the expression in the application expression library, so that the interaction effect is improved.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to a method, an apparatus, a device, and a computer-readable storage medium for message interaction. Background Art

[0002] In recent years, with the rapid development of computer technology, some virtual objects can help users process messages in a timely manner and improve message processing efficiency. For example, virtual objects can autonomously generate reply content for received messages, for example, to support the generation of response messages when the user is not online, or to process a large number of received messages in a timely manner. Generally speaking, virtual objects only support interaction with users through text mode. Summary of the invention

[0003] In a first aspect of the present disclosure, a message interaction method is provided. The method comprises: receiving a first message input by a user in an interaction interface with a virtual object; presenting a second message generated by the virtual object based on the first message; and providing a first expression associated with the second message, the first expression being determined from a preset first expression library based on the second message.

[0004] In a second aspect of the present disclosure, a device for message interaction is provided. The device includes: a receiving module configured to receive a first message input by a user in an interaction interface with a virtual object; a presenting module configured to present a second message generated by the virtual object based on the first message; and a providing module configured to provide a first expression associated with the second message, the first expression being determined from a preset first expression library based on the second message.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the device executes the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] It should be understood that the contents described in this content section are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0009] Figure 1 A schematic diagram showing an example environment in which embodiments according to the present disclosure may be implemented;

[0010] FIG. 2A to FIG. 2B shows an example interface according to some embodiments of the present disclosure;

[0011] Figure 2C An example process of determining an expression according to some embodiments of the present disclosure is shown;

[0012] Figure 3 A flowchart showing an example process of message interaction according to some embodiments of the present disclosure;

[0013] Figure 4 A schematic structural block diagram showing an example apparatus for message interaction according to some embodiments of the present disclosure; and

[0014] Figure 5 A block diagram of an electronic device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0015] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0016] It should be noted that the titles of any sections / subsections provided herein are not restrictive. Various embodiments are described throughout this article, and any type of embodiment may be included under any section / subsection. In addition, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0017] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part 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 may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0018] The embodiments of the present disclosure may involve user data, data acquisition and / or use, etc. These aspects are subject to the corresponding laws, regulations and relevant provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user knows and confirms. Accordingly, when implementing each embodiment of the present disclosure, the type, scope of use, usage scenario, etc. of the data or information that may be involved should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with the relevant laws and regulations. The specific notification and / or authorization method can vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this respect.

[0019] In this specification and the embodiments, if personal information processing is involved, it will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or it is necessary to perform a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0020] Traditionally, users can interact with virtual objects through dialogue, for example, to obtain response messages generated by virtual objects. Generally speaking, virtual objects only support interaction with users in text mode. On the one hand, such interaction forms are relatively simple and it is difficult to provide users with a real dialogue experience. On the other hand, this also limits the quality of the content generated by virtual objects.

[0021] The embodiment of the present disclosure proposes a message interaction scheme. According to the scheme, a first message input by a user can be received in an interaction interface with a virtual object. Further, a second message generated by the virtual object based on the first message can be presented. Additionally, a first expression associated with the second message can be provided, and the first expression is determined from a preset first expression library based on the second message.

[0022] In this way, the embodiments of the present disclosure can support virtual objects to reply to messages by calling expressions in the application expression library, thereby improving the interaction effect.

[0023] Various example implementations of the solution are described in detail below in conjunction with the accompanying drawings.

[0024] Example Environment

[0025] Figure 1 1 is a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. Figure 1 As shown, example environment 100 may include electronic device 110 .

[0026] In this example environment 100, the electronic device 110 may run an application 120 that supports interface interaction. The application 120 may be any appropriate type of application for interface interaction, examples of which may include, but are not limited to, instant messaging applications, video applications, social applications, or other appropriate applications. The user 140 may interact with the application 120 via the electronic device 110 and / or its attached devices.

[0027] exist Figure 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 interface interaction through the application 120.

[0028] In some embodiments, the electronic device 110 communicates with the server 130 to provide services for the application 120. The electronic device 110 can be any type of mobile terminal, fixed terminal or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a handheld computer, a portable game 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 receiver, an e-book device, a game device, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some embodiments, the electronic device 110 can also support any type of interface for the user (such as a "wearable" circuit, etc.).

[0029] The server 130 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as 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 big data and artificial intelligence platforms. The server 130 may include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, etc. The server 130 may provide background services for the application 120 that supports content presentation in the electronic device 110.

[0030] A communication connection may be established between the server 130 and the electronic device 110. The communication connection may be established in a wired manner or a wireless manner. The communication connection may include, but is not limited to, a Bluetooth connection, a mobile network connection, a Universal Serial Bus (USB) connection, a Wireless Fidelity (WiFi) connection, etc., and the embodiments of the present disclosure are not limited in this respect. In the embodiments of the present disclosure, the server 130 and the electronic device 110 may implement signaling interaction through the communication connection between the two.

[0031] It should be understood that the structure and function of the various elements in the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure.

[0032] Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings.

[0033] Example Interaction

[0034] The following will refer to FIG. 2A to FIG. 2B To describe some example interaction processes according to embodiments of the present disclosure. FIG. 2A to FIG. 2B Example interaction interfaces 200A to 200B according to some embodiments of the present disclosure are shown. For example, the interaction interfaces 200A to 200B may be composed of Figure 1 The electronic device 110 is provided as shown.

[0035] like Figure 2A As shown, the electronic device 110 can present an interaction interface 200A between the user and the virtual object 205. In some scenarios, the interaction interface may include a conversation interface associated with the virtual object 205. Such a conversation interface may be associated with a single chat session between the user and the virtual object 205, or a group chat session associated with the virtual object 205, for example.

[0036] In some other scenarios, the interaction interface may have other appropriate forms, for example, such as the interaction interface may correspond to the interaction space of the virtual object 205 , which may support the user to interact with the virtual object 205 in multiple modes.

[0037] In some embodiments, the virtual object 205 may be associated with a target user. As an example, the virtual object 205 may be created based on a configuration operation of the target user. When the target user authorizes the virtual object 205, for example, the virtual object 205 may also be created based on reference information of the target user.

[0038] For example, in some embodiments, a virtual object can be generated based on image data and a description text input by a user. A virtual object can include a visual representation of the virtual object and the capabilities of the virtual object (e.g., dialogue capabilities, data processing capabilities, etc.). In some scenarios, such a virtual object can also be referred to as a digital object or a virtual entity.

[0039] It should be understood that, on the one hand, a virtual object may have a virtual image for interaction. On the other hand, a virtual object may also utilize an appropriate model to drive its interactive behavior, and such a model may include any appropriate machine learning model, for example, a generative model. In the present disclosure, various interactive processes and / or generative operations performed by a virtual object may be actually performed using an appropriate model corresponding to the virtual object.

[0040] The following will describe the example interaction process of the present disclosure using the conversation interface as an example of the interaction interface. Figure 2A As shown, the electronic device 110 may provide an input control 225 in the interactive interface 200A. Further, the electronic device 110 may receive the first message 210 input by the user via the input control 225.

[0041] As an example, the first message 210 may include a message of any modality, examples of which may include but are not limited to: a text message, a voice message, an image message, a video message, and the like.

[0042] In some embodiments, Figure 2A As shown, the electronic device 110 can provide a second message 215 generated by the virtual object 205 based on the first message 210 in the interaction interface 200A. It should be understood that the virtual object 205 can process the first message 210 using an associated model to generate the second message 215.

[0043] In some embodiments, the virtual object 205 may, for example, be associated with a generative model, and the second message 215 may, for example, include text content, voice content, or other appropriate content generated by the generative model based on the first message 210 and / or contextual information associated with the first message 210.

[0044] Furthermore, the electronic device 110 may also provide a first expression 220 in the interaction interface 200A as at least part of the reply content to the first message 210. In some embodiments, the first expression 220 may be determined from a preset first expression library based on the first message 210.

[0045] In some embodiments, the interactive interface 200A may be associated with a target application, such as a video application, an instant messaging application, etc. The target application may be associated with an application expression library. As an example, the application expression library may be a public expression resource provided by the target application, and a user in the target application may obtain and use expressions in the application expression library.

[0046] by Figure 2A As an example, the second message 215 generated by the virtual object 205 may be related to "cat". Accordingly, the electronic device 110 may provide a first expression associated with "cat" from the application expression library as a reply to the first message 210, thereby enriching the content provided by the virtual object 205.

[0047] In this way, the embodiments of the present disclosure can support virtual objects to use existing expression resources in the target application to reply to messages input by users, thereby improving the message interaction experience.

[0048] In some embodiments, the first expression 220 may also be determined based on a target user associated with the virtual object 205. As discussed above, the virtual object 205 may be created based on a configuration operation of the target user, or the virtual object 205 may be created based on reference information of the target user.

[0049] Accordingly, the first expression 220 may also be related based on the associated information of the target user. As an example, the target user may configure the range of expressions that the virtual object is allowed to use when replying to a message. For example, the target user may configure the virtual object to allow the use of expressions that the target user has collected in the target application to reply to a message. For example, the first expression 220 may be an expression related to "cat" that the target user has collected in the target application.

[0050] As another example, the target user can also manage the expression library allowed to be used by the virtual object. For example, the target user can use the received expression or picture as the expression library allowed to be used by the virtual object during the use of the target application.

[0051] In some embodiments, the first expression 220 may also correspond to the expression search results of the target user in the target application. For example, the first expression 220 may correspond to the relevant expression search results presented when the target user inputs "cat" in the interactive interface.

[0052] Based on this approach, the expressions provided by the virtual objects during the interaction process can better match the target users, thus providing users with a more realistic interactive experience.

[0053] In some embodiments, only when it is determined that the generated second message 215 matches the first interaction scene, the electronic device 110 further provides the first expression 220. In some embodiments, an appropriate scene detection model can be used to determine whether the second message 215 matches the preset first interaction scene. The present disclosure is not intended to limit the specific implementation of the scene detection model.

[0054] In some embodiments, the first interactive scene may be determined based on a configuration operation of the target user. As an example, the target user may configure the virtual object to use expressions to reply to the user when the first type of topic is involved.

[0055] Further, the electronic device 110 and / or the server 130 may determine whether the second message 215 matches the first category topic to determine whether an expression for replying to the user can be further obtained from the first expression library. As an example, the first category topic configured by the user may include "animals". Accordingly, when it is determined that the second message 215 is about "cat", the electronic device 110 may further obtain the first expression 220 corresponding to "cat" from the first expression library, and may present it to the user in the interactive interface 200A accordingly.

[0056] In other embodiments, the target user may also configure the virtual object to prohibit the use of emoticons to reply to the user when the first category of topics is involved.

[0057] In some embodiments, the virtual object 205 may also be associated with a second expression library. The second expression library may include one or more expressions generated based on the virtual object. As described above, the virtual object 205 may have related image data, and the server 130 may pre-build a set of expressions based on the image data of the virtual object 205 as the second expression library.

[0058] In some embodiments, Figure 2B As shown, the electronic device 110 may receive a third message 230 input by a user, and may display a fourth message 235 generated by the virtual object 205 based on the third message 230. Figure 2ADifferent from the illustrated example, the electronic device 110 may present a second expression 240 determined from a second expression library.

[0059] like Figure 2B As shown, the electronic device 110 can present the second expression 240 generated based on the image data of the virtual object 205. In some embodiments, when the virtual object is associated with both the first expression library and the second expression library, the electronic device 110 and / or the server 130 can determine the output expression based on the degree of matching between the second message and the first expression library and the second expression library.

[0060] Alternatively, the electronic device 110 may also give priority to sending expressions in the first expression library, or give priority to sending expressions in the second expression library. As an example, the electronic device 110 may determine whether to give priority to using expressions in the first expression library or expressions in the second expression library based on the configuration operation of the target user.

[0061] In some other embodiments, when it is determined that the generated second message 235 matches the second interaction scenario, the electronic device 110 may, for example, provide a second expression determined from a second expression library. In some embodiments, the second interaction scenario may, for example, be determined based on a configuration operation or associated information of the target user.

[0062] In this way, the embodiments of the present disclosure can support virtual objects to mix and match expressions created based on virtual objects with expressions in an application expression library, thereby further enriching the types of expressions allowed for use in interactions and improving the experience of message interaction.

[0063] The following will further combine Figure 2C The specific process of determining the first expression 220 or the second expression 240 as mentioned above will be described.

[0064] like Figure 2C As shown, the server 130 may determine multiple expressions associated with the target user and / or the virtual object from the application expression library 250 based on the configuration operation 252 of the target user. Further, the server 130 may further construct a first expression library 254 from multiple expressions.

[0065] In some embodiments, the configuration operation 252 may include, for example, an authorization operation of the target user to indicate that the virtual object 205 is allowed to use the expressions in the application expression library 250. In some embodiments, the configuration operation 252 may also indicate, for example, the category of expressions to be added to the first expression library 254.

[0066] For example, the target user may indicate that the virtual object is allowed to use expressions of the “animal” category. Accordingly, the electronic device 110 may determine multiple expressions matching the “animal” category from the application expression library 250 to add to the first expression library 254 .

[0067] In some embodiments, one or more expressions added to the application expression library 250 may also be determined based on the description information of the target user and / or the virtual object. For example, with the authorization of the target user, the server 130 may filter multiple expressions associated with "food" based on the channel tag "food" corresponding to the target user to add to the first expression library 254.

[0068] As another example, the server 130 may also determine one or more expressions matching the description information from the application expression library 250 based on the description information (eg, setting information) of the virtual object 205 to add to the first expression library 254 .

[0069] For example, the server 130 may obtain the description text and / or system prompt item of the virtual object 205, and may determine that the virtual object 205 may correspond to a lively interactive style, for example. Further, the server 130 may determine one or more expressions matching the "lively style" from the application expression library 250 to add to the first expression library 254.

[0070] In addition, if Figure 2C As shown, in some scenarios, the expression generation tool 260 can also generate one or more expressions associated with the virtual object, and can build the second expression library 262 mentioned above. As an example, the expression generation tool 260 can generate expressions associated with different themes using, for example, an image generation model, and such expressions can have visual elements associated with the virtual object 205, for example.

[0071] Further, the expression library 256 that the virtual object 205 can use may include a union of the first expression library 254 and the second expression library 262. In some embodiments, the expression library 256 may be provided as knowledge information of the generative model 258 associated with the virtual object 205.

[0072] Thus, the model 258 can recall expressions suitable for replying to the message input by the user from the expression library 256 based on the context information.

[0073] Specifically, the model 258 can generate the corresponding second message 215 based on the first message 210 input by the user and the associated context message. Further, the model 258 can also determine at least one keyword based on the second message 215.

[0074] As an example, the model 258 can determine the text content corresponding to the second message 215, and can determine a set of candidate keywords from the text content. The semantic information and / or grammatical information of such a set of candidate keywords meet the preset conditions. It is understandable that when the second message includes voice content or other types of content other than text content, the other types of content can be converted into text content, and then a set of candidate keywords can be determined based on the converted text content.

[0075] Exemplarily, key semantic recognition may be performed on the text content corresponding to the second message, including identifying key phrases in the text content, and obtaining a group of candidate keywords through random screening and / or deduplication.

[0076] As an example, the model 258 may determine one or more keywords whose grammatical attributes are verbs from the text content corresponding to the second message 215. As an example, if the second message 215 includes the text "Kitten Drinks Water", the model 258 may determine the verb "drinks water" as a keyword.

[0077] In some embodiments, the model 258 may also determine a keyword whose semantic information satisfies the condition from the text content corresponding to the second message 215. For example, if the second message 215 includes the text "the kitten happily drinks water", the model 258 may determine "happy" whose semantic information satisfies the condition as a keyword.

[0078] Further, the language model may be used to process the second message 215 to determine a set of candidate keywords. As an example, the server 130 may provide the language model with the text content of the second message 215 and description information related to the preset condition. Further, the server 130 may obtain a set of candidate keywords that meet the preset condition and are output by the language model based on the text content.

[0079] In some embodiments, when a group of candidate keywords includes multiple keywords, the server 130 may also determine at least one keyword from the group of candidate keywords. For example, the server 130 may randomly select a predetermined number of keywords as at least one keyword to be used.

[0080] Further, the model 258 may perform a search based on the determined at least one keyword to determine an expression matching the at least one keyword from the expression library 256 .

[0081] In some embodiments, before executing the search process, the server 130 can also determine the expression interaction scene 264, and can determine based on the expression interaction scene 264 whether only the first expression library 254 can be used, only the second expression library 262 can be used, or both can be used.

[0082] As an example, when it is determined that only the first expression library 254 can be used, the server 130 can search the first expression library 254 based on at least one keyword, and thereby obtain the expression library 254 as follows: Figure 2A As another example, when it is determined that only the second expression library 262 can be used, the server 130 can search the second expression library 262 based on at least one keyword, and thereby obtain the first expression 220 shown in FIG. Figure 2B A second expression 240 is shown.

[0083] As yet some other examples, in the case of determining that only the first expression library 254 and the second expression library 262 can be used simultaneously, the server 130 may search the expression library 256 based on at least one keyword to determine the expression to be provided.

[0084] In some embodiments, when a group of candidate expressions are obtained by searching the first expression library 254, the second expression library 262 and / or the expression library 256, the server 130 can also determine the expression to be output from the group of candidate expressions based on the association between the group of candidate expressions and the virtual objects and / or the target user.

[0085] For example, the server 130 may determine an expression that best matches the target user and / or the virtual object from among the multiple candidate expressions obtained through the search, as the first expression 220 or the second expression 240 .

[0086] In this way, the embodiments of the present disclosure can more flexibly output expressions that better match the interaction scenario, thereby improving the effect of content interaction.

[0087] Example Process

[0088] Figure 3 FIG. 3 is a flow chart showing an example information interaction process 300 according to some embodiments of the present disclosure. The process 300 may be implemented at the electronic device 110. Figure 1 Process 300 is described.

[0089] like Figure 3 As shown, in box 310, the electronic device 110 receives a first message input by a user in an interaction interface with a virtual object;

[0090] In box 320, the electronic device 110 presents a second message generated by the virtual object based on the first message.

[0091] In box 330, the electronic device 110 provides a first expression associated with the second message, where the first expression is determined from a preset first expression library based on the second message.

[0092] In some embodiments, the first expression is determined based on an application expression library of a target application, where the target application is associated with an interactive interface; and / or the first expression is determined based on a target user associated with the virtual object.

[0093] In some embodiments, the first expression is determined based on the following process: determining at least one keyword based on the second message; and determining a first expression matching the at least one keyword from a first expression library.

[0094] In some embodiments, based on the second message, determining at least one keyword includes: determining a group of candidate keywords from the text content corresponding to the second message, the semantic information and / or grammatical information of the group of candidate keywords satisfying preset conditions; and determining at least one keyword from the group of candidate keywords.

[0095] In some embodiments, determining a set of candidate keywords from text content corresponding to the second message includes: providing the text content and description information associated with a preset condition to a target model; and obtaining a set of keywords determined by the target model.

[0096] In some embodiments, determining a first expression that matches at least one keyword from a first expression library includes: determining a group of candidate expressions that match at least one keyword from the first expression library; and determining the first expression from a group of candidate expressions based on an association between the group of candidate expressions and a virtual object and / or a target user, the target user being associated with the virtual object.

[0097] In some embodiments, the first expression library is constructed based on the following process: in response to receiving a configuration operation of a target user associated with a virtual object, determining multiple expressions associated with the target user and / or the virtual object from the application expression library; and constructing the first expression library based on the multiple expressions.

[0098] In some embodiments, the first expression library is provided as knowledge information of a generative model associated with the virtual object.

[0099] In some embodiments, providing the first expression associated with the second message includes: in response to the generated second message matching the first interaction scenario, providing the first expression associated with the second message.

[0100] In some embodiments, the virtual object is also associated with a second expression library, which includes multiple expressions generated based on the virtual object. The method also includes: in response to the generated second message matching the second interactive scene, providing a second expression determined from the second expression library.

[0101] Example devices and equipment

[0102] The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Figure 4 A schematic structural block diagram of an example apparatus 400 for interface interaction according to some embodiments of the present disclosure is shown. The apparatus 400 may be implemented as or included in the electronic device 110. Each module / component in the apparatus 400 may be implemented by hardware, software, firmware, or any combination thereof.

[0103] like Figure 4 As shown, the device 400 includes: a receiving module 410, configured to receive a first message input by a user in an interaction interface with a virtual object; a presenting module 420, configured to present a second message generated by the virtual object based on the first message; and a providing module 430, configured to provide a first expression associated with the second message, the first expression being determined from a preset first expression library based on the second message.

[0104] In some embodiments, the first expression is determined based on an application expression library of a target application, where the target application is associated with an interactive interface; and / or the first expression is determined based on a target user associated with the virtual object.

[0105] In some embodiments, the first expression is determined based on the following process: determining at least one keyword based on the second message; and determining a first expression matching the at least one keyword from a first expression library.

[0106] In some embodiments, based on the second message, determining at least one keyword includes: determining a group of candidate keywords from the text content corresponding to the second message, the semantic information and / or grammatical information of the group of candidate keywords satisfying preset conditions; and determining at least one keyword from the group of candidate keywords.

[0107] In some embodiments, determining a set of candidate keywords from text content corresponding to the second message includes: providing the text content and description information associated with a preset condition to a target model; and obtaining a set of keywords determined by the target model.

[0108] In some embodiments, determining a first expression that matches at least one keyword from a first expression library includes: determining a group of candidate expressions that match at least one keyword from the first expression library; and determining the first expression from a group of candidate expressions based on an association between the group of candidate expressions and a virtual object and / or a target user, the target user being associated with the virtual object.

[0109] In some embodiments, the first expression library is constructed based on the following process: in response to receiving a configuration operation of a target user associated with a virtual object, determining multiple expressions associated with the target user and / or the virtual object from the application expression library; and constructing the first expression library based on the multiple expressions.

[0110] In some embodiments, the first expression library is provided as knowledge information of a generative model associated with the virtual object.

[0111] In some embodiments, providing the first expression associated with the second message includes: in response to the generated second message matching the first interaction scenario, providing the first expression associated with the second message.

[0112] In some embodiments, the virtual object is also associated with a second expression library, which includes multiple expressions generated based on the virtual object. The method also includes: in response to the generated second message matching the second interactive scene, providing a second expression determined from the second expression library.

[0113] The modules included in the device 400 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units can be implemented using software and / or firmware, such as machine executable instructions stored on a storage medium. In addition to or as an alternative to machine executable instructions, some or all of the modules in the device 400 can be implemented at least in part by one or more hardware logic components. As an example and not limitation, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0114] like Figure 5 As shown, the electronic device 500 is in the form of a general electronic device. The components of the electronic device 500 may include, but are not limited to, one or more processors or processing units 510, a memory 520, a storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processing unit 510 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 520. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 500.

[0115] The electronic device 500 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 520 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 530 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 500.

[0116] The electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 5 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 520 may include a computer program product 525 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0117] The communication unit 540 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 500 can be implemented in a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 500 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0118] The input device 550 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 560 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 500 may also communicate with one or more external devices (not shown) through the communication unit 540 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 500, or communicate with any device that allows the electronic device 500 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0119] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0120] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0121] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0122] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0123] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0124] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A message interaction method, comprising: In an interactive interface with a virtual object, receiving a first message input by a user; presenting a second message generated by the virtual object based on the first message; as well as A first expression associated with the second message is provided, where the first expression is determined from a preset first expression library based on the second message.

2. The method according to claim 1, wherein: The first expression is determined based on an application expression library of a target application, and the target application is associated with the interactive interface; and / or The first expression is determined based on a target user associated with the virtual object.

3. The method according to claim 1, wherein the first expression is determined based on the following process: Based on the second message, determining at least one keyword; and The first expression matching the at least one keyword is determined from the first expression library.

4. The method of claim 3, wherein based on the second message, determining at least one keyword comprises: Determine a group of candidate keywords from the text content corresponding to the second message, wherein semantic information and / or grammatical information of the group of candidate keywords meets a preset condition; as well as The at least one keyword is determined from the set of candidate keywords.

5. The method of claim 4, wherein determining a set of candidate keywords from text content corresponding to the second message comprises: Providing the text content and the description information associated with the preset condition to the target model; as well as The set of keywords determined by the target model is obtained.

6. The method according to claim 3, wherein determining the first expression matching the at least one keyword from the first expression library comprises: Determining, from the first expression library, a group of candidate expressions matching the at least one keyword; as well as The first expression is determined from the set of candidate expressions based on an association between the set of candidate expressions and the virtual object and / or a target user associated with the virtual object.

7. The method according to claim 1, wherein the first expression library is constructed based on the following process: In response to receiving a configuration operation of a target user associated with the virtual object, determining a plurality of expressions associated with the target user and / or the virtual object from an application expression library; and Based on the multiple expressions, the first expression library is constructed. 8 . The method according to claim 1 , wherein the first expression library is provided as knowledge information of a generative model associated with the virtual object.

9. The method of claim 1, wherein providing a first emoticon associated with the second message comprises: In response to the generated second message matching the first interaction scenario, providing the first expression associated with the second message.

10. The method according to claim 9, wherein the virtual object is further associated with a second expression library, the second expression library comprising a plurality of expressions generated based on the virtual object, the method further comprising: In response to the generated second message matching the second interactive scenario, providing the second expression determined from the second expression library.

11. A device for message interaction, comprising: A receiving module, configured to receive a first message input by a user in an interaction interface with a virtual object; a presentation module, configured to present a second message generated by the virtual object based on the first message; as well as The providing module is configured to provide a first expression associated with the second message, where the first expression is determined from a preset first expression library based on the second message.

12. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 10 when executed by the at least one processing unit.

13. A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1 to 10 when executed by a processor.

Images