Information interaction method and apparatus, device, storage medium, and program product

Abstract

Embodiments of the present disclosure relate to an information interaction method and apparatus, a device, a storage medium, and a program product. The method provided herein comprises: receiving a first input message in a first session interface of a target session performed with a first virtual object; providing a first set of response messages in the session interface, the first set of response messages comprising a first response message generated by the first virtual object and a second response message generated by a second virtual object, and the second virtual object being independent of the target session; and presenting, in association with the second response message, reference information associated with the second virtual object.

Description

Methods, apparatus, devices, storage media and program products for information exchange

[0001] This application claims priority to Chinese Patent Application No. 202411645629.1, filed on November 15, 2024, entitled "Method, Apparatus, Device and Storage Medium for Information Interaction", the entire contents of which are incorporated herein by reference. Technical Field

[0002] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to methods, apparatuses, devices, computer-readable storage media, and computer program products for information interaction. Background Technology

[0003] In recent years, with the rapid development of computer technology, some virtual objects have emerged that can help users process messages promptly and improve message processing efficiency. For example, virtual objects can autonomously generate responses to received messages, such as supporting the generation of response messages when users are offline, or processing large numbers of received messages in a timely manner. Summary of the Invention

[0004] In a first aspect of this disclosure, a method for information interaction is provided. The method includes: receiving a first input message in a first session interface of a target session with a first virtual object; providing a first set of response messages in the session interface, the first set of messages including a first response message generated by the first virtual object and a second response message generated by a second virtual object, the second virtual object being independent of the target session; and presenting reference information associated with the second virtual object in conjunction with the second response message.

[0005] In a second aspect of this disclosure, an apparatus for information interaction is provided. The apparatus includes: a receiving module configured to receive a first input message in a first session interface of a target session with a first virtual object; a providing module configured to provide a first set of response messages in the session interface, the first set of messages including a first response message generated by the first virtual object and a second response message generated by a second virtual object, the second virtual object being independent of the target session; and a presenting module configured to present reference information associated with the second virtual object in connection with the second response message.

[0006] In a third aspect of this disclosure, an electronic device is provided. The device includes 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. When executed by the at least one processor, the instructions cause the device to perform the method of the first aspect.

[0007] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions that can be executed by a processor to implement the method of the first aspect.

[0008] In a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program executable by a processor to implement the method of the first aspect.

[0009] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0011] Figure 1 shows a schematic diagram of an example environment in which embodiments of the present disclosure may be implemented;

[0012] Figures 2A to 2D illustrate example interfaces according to some embodiments of the present disclosure;

[0013] Figure 3 illustrates a schematic diagram of an example process for generating a response message according to some embodiments of the present disclosure;

[0014] Figure 4 illustrates a flowchart of an example process of information interaction according to some embodiments of the present disclosure;

[0015] Figure 5 shows a schematic structural block diagram of an example device for information interaction according to some embodiments of the present disclosure; and

[0016] Figure 6 shows a block diagram of an electronic device capable of implementing several embodiments of the present disclosure. Detailed Implementation

[0017] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0018] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0019] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, 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 may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0020] The embodiments of this disclosure may involve user data, data acquisition, and / or use. All of these aspects comply with applicable laws, regulations, and relevant provisions. In the embodiments of this disclosure, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, in implementing the embodiments of this disclosure, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained in accordance with relevant laws and regulations through appropriate means. The specific methods of notification and / or authorization may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited in this respect.

[0021] In this specification and the embodiments, any processing of personal information will be carried out only under the premise of legality (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information other than that necessary for basic functions will not affect the user's use of basic functions.

[0022] Traditionally, users interact with virtual objects, for example, through dialogue, to obtain response messages generated by the virtual objects. Generally, depending on the virtual object's configuration and training data, virtual objects have better processing capabilities in certain specific domains. For example, some virtual objects may be trained to handle mathematical problems better, but they may struggle to provide high-quality translations for users.

[0023] The embodiments of this disclosure propose an information interaction scheme. According to this scheme, a first input message can be received in a first session interface of a target session with a first virtual object. Further, a first set of response messages can be provided in the session interface, the first set of messages including a first response message generated by the first virtual object and a second response message generated by a second virtual object, the second virtual object being independent of the target session. Additionally, reference information associated with the second virtual object can be presented in conjunction with the second response message.

[0024] In this way, embodiments of the present disclosure can provide messages generated by different virtual objects in a session with a single virtual object, thereby helping to obtain higher quality content and improve the efficiency of information retrieval.

[0025] The following section provides a detailed description of various example implementations of this scheme, with reference to the accompanying drawings.

[0026] Example Environment

[0027] Figure 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in Figure 1, the example environment 100 may include an electronic device 110.

[0028] In this example environment 100, electronic device 110 may run an application 120 that supports user interface interaction. Application 120 may be any suitable type of application for user interface interaction, and examples may include, but are not limited to, search applications, video applications, social applications, or other suitable applications. User 140 may interact with application 120 via electronic device 110 and / or its attached devices.

[0029] In environment 100 of Figure 1, if application 120 is active, electronic device 110 can use application 120 to present interface 150 for supporting interface interaction.

[0030] In some embodiments, electronic device 110 communicates with server 130 to provide services to application 120. Electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable gaming terminals, VR / AR devices, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, electronic device 110 can also support any type of user-facing interface (such as "wearable" circuitry).

[0031] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for applications 120 that support content presentation in electronic devices 110.

[0032] A communication connection can be established between server 130 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection may include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (WiFi) connections; the embodiments of this disclosure are not limited in this respect. In the embodiments of this disclosure, server 130 and electronic device 110 can achieve signaling interaction through the communication connection between them.

[0033] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0034] The following description will continue with reference to the accompanying drawings, which will provide some exemplary embodiments of this disclosure.

[0035] Example Interaction

[0036] Figures 2A to 2D illustrate example interfaces 200A to 200D according to some embodiments of the present disclosure. Interfaces 200A to 200D may be provided, for example, by the electronic device 110 shown in Figure 1.

[0037] As shown in Figure 2A, interface 200A can be a session interface associated with virtual object A. In some scenarios, such virtual object A can correspond to an appropriate user associated with function 140, which may be created, for example, based on the user's configuration operations.

[0038] It should be understood that, on the one hand, a virtual object can have a virtual avatar for interaction. On the other hand, a virtual object can also utilize an appropriate model to drive its interactive behavior, such a model can include any suitable machine learning model, for example, a generative model. In this disclosure, the various interactive processes and / or generative operations performed by the virtual object can be actually performed using an appropriate model corresponding to the virtual object.

[0039] As shown in Figure 2A, the conversation corresponding to interface 200A can be a one-on-one chat between the current user and the virtual object, or it can be a group chat with participants including the current user and the virtual object.

[0040] In some embodiments, the electronic device 110 may receive a first input message 210 sent by a user via the input control 205. It should be understood that such a first message can take any suitable form, examples of which may include, but are not limited to, text messages, emoticon messages, voice messages, video messages, image messages, or combinations thereof. As an example, the first input message 210 may include the text “What are some recommended books?”.

[0041] As shown in Figure 2A, the electronic device 110 can provide response messages based on a first set of response messages, such as response message 215, response message 220, response message 225 and response message 230, in the session interface 200A.

[0042] In some embodiments, response message 215 and response message 220 may be generated by the virtual object A based on the received first input message 210. As an example, response message 215 and / or response message 220 may be generated by the target model corresponding to the virtual object A.

[0043] As an example, virtual object A can process the first input message 210 based on configuration information (such as system prompts, knowledge bases, etc.) to generate a response message 215. As an example, response message 215 could be something like, "Book A and Book B are both good choices!"

[0044] In some embodiments, response message 225 and response message 230 may be generated by virtual objects other than virtual object A. For example, response message 225 may be generated by virtual object B based on the first input message 210, and response message 230 may be generated by virtual object C based on the first input message 210. The specific process for determining virtual object B and virtual object C will be described below with reference to FIG3, and will not be described in detail here.

[0045] As an example, virtual object B can process the first input message 210 based on configuration information (such as system prompts, knowledge bases, etc.) to generate a response message 225. As an example, response message 225 could be, "I think Book C and Book D are good!"

[0046] As an example, virtual object C can process the first input message 210 based on configuration information (such as system prompts, knowledge bases, etc.) to generate a response message 230. As an example, response message 230 could be "You can try Book E!".

[0047] In some embodiments, virtual object B and virtual object C may be independent of the current session. For example, neither virtual object B nor virtual object C is a participant in the current session, and / or neither virtual object B nor virtual object C has been added to the session by the user of the current session.

[0048] As an example, in a one-on-one chat scenario where the current session is between a user and virtual object A, other virtual objects that are different from virtual object A can be understood as independent of the current session. As an example, in a group chat scenario where the current session is between a user and virtual object A, virtual objects that are not participants in the group chat can be understood as independent of the current session.

[0049] In some embodiments, to facilitate user perception that response message 225 and / or response message 230 originate from other virtual objects, electronic device 110 may also associate response message 225 with presenting reference information 228 associated with virtual object B. Alternatively, electronic device 110 may also associate response message 230 with presenting reference information 232 associated with virtual object C.

[0050] As an example, reference information 228 or reference information 232 may include identification information of virtual object B or virtual object C, such as text identification or image identification.

[0051] Additionally, the response message 220 generated by virtual object A may also include a content portion associated with the second response message. For example, response message 220 may include "Virtual object B and virtual object C also have their recommendations!".

[0052] In this way, embodiments of this disclosure can provide messages generated by different virtual objects within a session with a single virtual object, thereby helping to obtain higher-quality content and improve the efficiency of information retrieval. For example, taking the scenario in Figure 2A as an example, a user can obtain book recommendations from different virtual objects, thereby improving the comprehensiveness of information retrieval.

[0053] Furthermore, the electronic device 110 can also receive the user's selection of the response message 225 and can present a session interface 200B as shown in FIG2B. This session interface 200B can correspond to the session between the user and the virtual object B.

[0054] In some embodiments, the electronic device 110 may present one or more related messages from the session interface 200A in the session interface 200B. For example, the electronic device 110 may present a first input message 210 in the session interface 200B and may present a response message 225 generated by the virtual object B.

[0055] In some embodiments, to facilitate user awareness that the first input message 210 originates from another session, the electronic device 110 may also display a prompt element 238 associated with the first input message 210 in the session interface 200B. As an example, the prompt element 238 may indicate that the first input message 210 originates from a session with another virtual object.

[0056] Furthermore, the electronic device 110 can also receive the second input message 235 via, for example, the input control 245 in the session interface 200B. Furthermore, the electronic device 110 can provide a response message 240 in the session interface 200B.

[0057] In some embodiments, the second virtual object may generate the response message 240 based solely on the second input message 235. Alternatively, the second virtual object may also generate the response message 240 based on the second input message and context information. In some embodiments, the context information may be determined, for example, based on the first input message 210 and / or the response message 225 in the session.

[0058] In this way, embodiments of the present disclosure can maintain contextual continuity during the switching to a session with other virtual dialogues and support users initiating multi-turn dialogues, thereby improving the efficiency of information interaction.

[0059] In some embodiments, as shown in FIG2C, the electronic device 110 may also support multi-turn dialogue interaction in a session with virtual object A. As an example, the electronic device 110 may obtain a third input message 250 via input control 205. For example, the third input message 250 may be "Recommend some music to listen to while reading".

[0060] Furthermore, the electronic device 110 may provide a second set of response messages in the session interface 200C. For example, the second set of response messages may include response message 255, response message 260, response message 265, and response message 270.

[0061] In some embodiments, response messages 255 and 260 may be generated by the virtual object A based on the received third input message 250. As an example, response messages 255 and / or 260 may be generated by the target model corresponding to the virtual object A.

[0062] In some embodiments, virtual object A may also generate response message 255 and / or response message 260 based on context information associated with the current session. In some embodiments, such context information may include the first input message 210 mentioned above and response message 215 and / or response message 220 generated by virtual object A.

[0063] In some embodiments, historical response messages generated by other virtual objects may also be provided to determine contextual information. For example, virtual object A may also generate response message 255 and / or response message 260 based on response message 225 and / or response message 230. As an example, response message 255 could be “Song A, you can try it!”

[0064] In some embodiments, response message 265 and response message 270 may be generated by virtual objects other than virtual object A. As an example, response message 265 may be generated by virtual object B based on second input message 250, and response message 270 may be generated by virtual object D based on second input message 250.

[0065] In some embodiments, the generation of response message 265 or response message 270 may also be based on context information in the current session. In some embodiments, when a preset condition is met, electronic device 110 may trigger virtual object B or virtual object D to generate a corresponding response message based on context information in the current session.

[0066] In some embodiments, when a multi-turn dialogue involves using the same virtual object to provide response messages, historical messages corresponding to that same virtual object can be provided as contextual information. For example, virtual object B can also generate response message 265 based on the first input message 210 and / or historically generated response messages 225 of virtual object B. As an example, response message 265 may include “I think Book C and Song B are a perfect match!”

[0067] In some embodiments, when the correlation between input messages in a multi-turn dialogue is higher than a threshold, one or more historical messages in the session can be provided as contextual information. For example, if the correlation between the first input message 210 and the third input message 250 is determined to be greater than a threshold, the first input message 210 and / or the previously generated response message 225 of the virtual object B are provided to the virtual object B to generate response message 265.

[0068] In some embodiments, the other virtual objects invoked for different input messages can be determined independently based on the input messages in each round. For example, in the example of FIG2A, virtual objects B and C can be determined from the set of virtual objects based on the first input message 210. In the example of FIG2C, virtual objects B and D can be determined from the set of virtual objects based on the third input message 250, and this can be regardless of whether virtual object B or virtual object C was invoked in the previous round.

[0069] In some embodiments, in a multi-turn dialogue scenario, the embodiments of this disclosure may, for example, determine the virtual object to be invoked in the current turn of the dialogue based on the virtual object invoked in the previous turn. For example, upon receiving a third input message 250, the embodiments of this disclosure may first determine whether virtual object B or virtual object C is suitable for processing the third input message 250. If it is determined that virtual object B is suitable for processing the third input message 250, virtual object B may be invoked to generate a response message for the third input message 250.

[0070] In other embodiments, during the generation of response message 270 by virtual object D, one or more response messages from previous dialogue rounds may be provided to virtual object D as contextual information, regardless of whether virtual object D has been invoked before. For example, virtual object D may generate response message 270 for the third input message 250 based on response message 225 or response message 230. As an example, response message 270 could be "Songs C and D are perfect for listening to while reading!"

[0071] In some embodiments, as shown in FIG2D, during the process of electronic device 110 providing response messages generated by other virtual objects, electronic device 110 may, for example, serially provide multiple response messages generated by virtual objects based on the first input message 210. For example, electronic device 110 may first stream response message 225 generated by virtual object B, and then stream response message 230 generated by virtual object C.

[0072] Alternatively, the electronic device 110 may also provide, for example, multiple response messages generated by multiple virtual objects based on the first input message in parallel. For example, the electronic device 110 may stream response message 225 generated by virtual object B and response message 230 generated by virtual object C in parallel within a session interface.

[0073] In some embodiments, the electronic device 110 may also receive appropriate types of operations in response to response messages generated by other virtual objects. For example, the electronic device 110 may receive feedback operations from the user in response to response message 225 generated by virtual object B and / or response message 230 generated by virtual object C. Alternatively, the electronic device 110 may also receive selections from the user in response to response message 225 generated by virtual object B and / or response message 230 generated by virtual object C, and may share them in other sessions.

[0074] The following description will further refer to FIG3 to illustrate an example process for generating a response message. FIG3 illustrates a schematic diagram of an example process 300 for generating a response message according to some embodiments of the present disclosure. As shown in FIG3, in response to receiving an input message in a session with a primary virtual object 310 (e.g., virtual object A in the examples of FIG2A to FIG2D), the input message and context information (e.g., the historical context associated with the session) 315 can be provided to the primary virtual object 310. The primary virtual object 310 can generate corresponding response content 315 based on its configuration information (such as system prompts, knowledge bases, etc.).

[0075] Additionally, the input message and context information 315 may also be provided to the virtual object agent 320. In some embodiments, the virtual object agent 320 may determine, based on the input message and context information 315, whether it is necessary to invoke other virtual objects to process the input message.

[0076] For example, the virtual object proxy 320 can determine whether to invoke other virtual objects based on the degree of matching between the input message and the main virtual object 310. Further, if it is determined that other virtual objects should be invoked, the virtual object proxy 320 can determine the relevance of the input message to multiple candidate virtual objects based on the input message and context information 315. As an example, such candidate virtual objects may include any appropriate virtual objects authorized for use by their publisher or administrator.

[0077] Furthermore, the virtual object agent 320 can determine one or more other virtual objects 330 that are different from the main virtual object from a plurality of candidate virtual objects based on the determined relevance. Further, input messages and context information 315 can be provided to the one or more other virtual objects 330 to generate corresponding response messages 335.

[0078] In some embodiments, in order to ensure the quality of the invoked virtual object, the virtual object agent 320 may first determine a set of candidate virtual objects from a plurality of candidate virtual objects, wherein the correlation between the input message and the set of candidate virtual objects is higher than a threshold.

[0079] Furthermore, the virtual object agent 320 may, for example, determine one or more other virtual objects 330 from a set of candidate virtual objects based on evaluation information 325 associated with that set of candidate virtual objects. As an example, the virtual object agent 320 may rank the set of candidate virtual objects based on the evaluation information 325 and select a predetermined number of virtual objects that rank highly. In some embodiments, such evaluation information 325 may indicate, for example, the domain that the virtual object excels at, the virtual object's RAG (Retrieval-augmented Generation) score, etc. As an example, the number of one or more other virtual objects 330 determined by the virtual object agent 320 is less than a preset number. In this way, embodiments of the present disclosure can invoke other virtual objects that are more closely matched to the input message to provide a corresponding response message, thereby improving the quality of the generated response message.

[0080] Example process

[0081] Figure 4 shows a flowchart of an example information interaction process 400 according to some embodiments of the present disclosure. Process 400 can be implemented at electronic device 110. Process 400 is described below with reference to Figure 1.

[0082] As shown in Figure 4, in box 410, electronic device 110 receives a first input message in the first session interface of the target session with the first virtual object.

[0083] In box 420, electronic device 110 provides a first set of response messages in a session interface. The first set of messages includes a first response message generated by a first virtual object and a second response message generated by a second virtual object, which is independent of the target session.

[0084] In box 430, electronic device 110 is associated with a second response message, presenting reference information associated with the second virtual object.

[0085] In some embodiments, process 400 further includes: in response to selection of a second response message, presenting a second session interface with the second virtual object; and presenting a first input message and a second response message in the second session interface.

[0086] In some embodiments, process 400 further includes: in response to receiving a second input message in a second session interface, providing a third response message, the third response message being generated by a second virtual object based on the second input message and first context information, wherein the first context information is determined based on the first input message and / or the second response message.

[0087] In some embodiments, process 400 further includes: presenting a prompt element associated with the first input message in a second session interface, the prompt element indicating that the first input message originates from a session with another virtual object.

[0088] In some embodiments, the second virtual object includes at least one virtual object determined from a set of virtual objects based on the first input message.

[0089] In some embodiments, the second virtual object includes multiple virtual objects, and the process 400 further includes: providing multiple response messages generated by the multiple virtual objects based on the first input message in parallel; or providing multiple response messages generated by the multiple virtual objects based on the first input message serially.

[0090] In some embodiments, the first response message includes a content portion associated with the second response message.

[0091] In some embodiments, process 400 further includes: in response to receiving a third input message in the session interface, providing a second set of response messages, the second set of messages including a third response message generated by a first virtual object and a fourth response message generated by the third virtual object.

[0092] In some embodiments, process 400 further includes: in response to determining that a preset condition is met, triggering a third virtual object to generate a fourth response message based on second context information, wherein the second context information is determined based on the first input message and / or the second response message.

[0093] In some embodiments, the preset conditions include: the third virtual object is the same as the second virtual object; and / or the correlation between the first input message and the third input message is greater than a threshold.

[0094] In some embodiments, the third virtual object is determined based on a third input message, and the determination of the third virtual object is independent of the second virtual object.

[0095] In some embodiments, the third response message is also generated based on the second response message.

[0096] In some embodiments, the second response message is generated based on the following process: determining the relevance of the first input message to a plurality of candidate virtual objects based on the first input message and the historical context associated with the target session; determining a second virtual object from the plurality of candidate virtual objects based on the relevance; and providing the first input message to the second virtual object to generate the second response message.

[0097] In some embodiments, determining a second virtual object from a plurality of candidate virtual objects based on correlation includes: determining a set of candidate virtual objects from a plurality of candidate virtual objects, wherein the correlation between the first input message and the set of candidate virtual objects is higher than a threshold; and determining a second virtual object from the set of candidate virtual objects based on evaluation information associated with the set of candidate virtual objects.

[0098] In some embodiments, the number of second virtual objects is less than a preset number.

[0099] Example devices and equipment

[0100] Embodiments of this disclosure also provide corresponding apparatus for implementing the methods or processes described above. Figure 5 shows a schematic structural block diagram of an example apparatus 500 for information interaction according to certain embodiments of this disclosure. Apparatus 500 may be implemented as or included in electronic device 110. The various modules / components in apparatus 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0101] As shown in Figure 5, the device 500 includes a receiving module 510 configured to receive a first input message in a first session interface of a target session with a first virtual object; a providing module 520 configured to provide a first set of response messages in the session interface, the first set of messages including a first response message generated by the first virtual object and a second response message generated by a second virtual object, the second virtual object being independent of the target session; and a presenting module 530 configured to present reference information associated with the second virtual object in connection with the second response message.

[0102] In some embodiments, the device 500 further includes a switching module configured to: present a second session interface with the second virtual object in response to the selection of the second response message; and present a first input message and a second response message in the second session interface.

[0103] In some embodiments, the switching module is further configured to: in response to receiving a second input message in a second session interface, provide a third response message, the third response message being generated by a second virtual object based on the second input message and first context information, wherein the first context information is determined based on the first input message and / or the second response message.

[0104] In some embodiments, the switching module is further configured to: present a prompt element associated with the first input message in the second session interface, the prompt element indicating that the first input message comes from a session with another virtual object.

[0105] In some embodiments, the second virtual object includes at least one virtual object determined from a set of virtual objects based on the first input message.

[0106] In some embodiments, the second virtual object includes multiple virtual objects, and the providing module 520 is further configured to: provide multiple response messages generated by the multiple virtual objects based on the first input message in parallel; or provide multiple response messages generated by the multiple virtual objects based on the first input message in serial order.

[0107] In some embodiments, the first response message includes a content portion associated with the second response message.

[0108] In some embodiments, the device 500 further includes a dialogue module configured to: in response to receiving a third input message in the dialogue interface, provide a second set of response messages, the second set of messages including a third response message generated by a first virtual object and a fourth response message generated by the third virtual object.

[0109] In some embodiments, the device 500 further includes a triggering module configured to: in response to determining that a preset condition is met, trigger a third virtual object to generate a fourth response message based on second context information, wherein the second context information is determined based on the first input message and / or the second response message.

[0110] In some embodiments, the preset conditions include: the third virtual object is the same as the second virtual object; and / or the correlation between the first input message and the third input message is greater than a threshold.

[0111] In some embodiments, the third virtual object is determined based on a third input message, and the determination of the third virtual object is independent of the second virtual object.

[0112] In some embodiments, the third response message is also generated based on the second response message.

[0113] In some embodiments, the second response message is generated based on the following process: determining the relevance of the first input message to a plurality of candidate virtual objects based on the first input message and the historical context associated with the target session; determining a second virtual object from the plurality of candidate virtual objects based on the relevance; and providing the first input message to the second virtual object to generate the second response message.

[0114] In some embodiments, determining a second virtual object from a plurality of candidate virtual objects based on correlation includes: determining a set of candidate virtual objects from a plurality of candidate virtual objects, wherein the correlation between the first input message and the set of candidate virtual objects is higher than a threshold; and determining a second virtual object from the set of candidate virtual objects based on evaluation information associated with the set of candidate virtual objects.

[0115] In some embodiments, the number of second virtual objects is less than a preset number.

[0116] The modules included in device 500 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 device 500 can be implemented at least partially by one or more hardware logic components. By way of 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 so on.

[0117] As shown in Figure 6, electronic device 600 is in the form of a general-purpose electronic device. Components of electronic device 600 may include, but are not limited to, one or more processors 610, memory 620, storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. Processor 610 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 620. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 600.

[0118] Electronic device 600 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 620 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 630 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 600.

[0119] Electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 5, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks may be provided. In these cases, each drive may be connected to a bus (not shown) via one or more data media interfaces. Memory 620 may include computer program product 625 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0120] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 600 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 600 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0121] Input device 650 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 660 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 600 can also communicate with one or more external devices (not shown) via communication unit 640 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 600, or with any device that enables electronic device 600 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0122] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0123] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0124] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0125] Computer-readable program instructions can 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 data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0126] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0127] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for information exchange, comprising: In the first session interface of the target session with the first virtual object, the first input message is received; In the session interface, a first set of response messages is provided, the first set of messages including a first response message generated by the first virtual object and a second response message generated by a second virtual object, the second virtual object being independent of the target session; as well as Associated with the second response message, reference information related to the second virtual object is presented.

2. The method according to claim 1, further comprising: In response to a selection of the second response message, a second session interface with the second virtual object is presented; as well as The first input message and the second response message are presented in the second session interface.

3. The method according to claim 2, further comprising: In response to receiving a second input message in the second session interface, a third response message is provided, the third response message being generated by the second virtual object based on the second input message and first context information, wherein the first context information is determined based on the first input message or the second response message.

4. The method according to claim 2, further comprising: In the second session interface, a prompt element associated with the first input message is presented, indicating that the first input message comes from a session with another virtual object.

5. The method of claim 1, wherein the second virtual object comprises at least one virtual object determined from a set of virtual objects based on the first input message.

6. The method of claim 5, wherein the second virtual object comprises a plurality of virtual objects, and the method further comprises: The multiple virtual objects are provided in parallel with multiple response messages generated based on the first input message; or The multiple virtual objects are provided serially with multiple response messages generated based on the first input message.

7. The method according to any one of claims 1 to 6, wherein the first response message includes a content portion associated with the second response message.

8. The method according to any one of claims 1 to 7, further comprising: In response to receiving a third input message in the session interface, a second set of response messages is provided, the second set of messages including a third response message generated by the first virtual object and a fourth response message generated by the third virtual object.

9. The method according to claim 8, further comprising: In response to the determination that a preset condition is met, the third virtual object is triggered to generate the fourth response message based on the second context information, which is determined based on the first input message or the second response message.

10. The method according to claim 9, wherein the preset conditions include: The third virtual object is the same as the second virtual object; or The correlation between the first input message and the third input message is greater than a threshold.

11. The method of claim 8, wherein the third virtual object is determined based on the third input message, and the determination of the third virtual object is independent of the second virtual object.

12. The method of claim 8, wherein the third response message is further generated based on the second response message.

13. The method according to any one of claims 1 to 12, wherein the second response message is generated based on the following process: Based on the first input message and the historical context associated with the target session, the relevance of the first input message to multiple candidate virtual objects is determined; Based on the correlation, the second virtual object is determined from the plurality of candidate virtual objects; as well as The first input message is provided to the second virtual object to generate the second response message.

14. The method of claim 13, wherein determining the second virtual object from the plurality of candidate virtual objects based on the correlation comprises: A set of candidate virtual objects is determined from the plurality of candidate virtual objects, wherein the correlation between the first input message and the set of candidate virtual objects is higher than a threshold. as well as The second virtual object is determined from the set of candidate virtual objects based on the evaluation information associated with the set of candidate virtual objects.

15. The method according to any one of claims 1 to 14, wherein the number of the second virtual objects is less than a preset number.

16. An apparatus for information interaction, comprising: The receiving module is configured to receive a first input message in a first session interface of a target session with a first virtual object; A module is configured to provide a first set of response messages in the session interface, the first set of messages including a first response message generated by a first virtual object and a second response message generated by a second virtual object, the second virtual object being independent of the target session; as well as The presentation module is configured to be associated with the second response message and to present reference information associated with the second virtual object.

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, when executed by a processor, implement the method according to any one of claims 1 to 15.

19. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 15.

Images