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

Abstract

Provided in the embodiments of the present disclosure is an information processing solution. A method (200) comprises: in response to detecting in an interactive interface a predetermined mention symbol that is input by a user, providing the presentation of a digital assistant list in the interactive interface on the basis of at least one of interactive context information in the interactive interface and at least one historical interactive operation of the user for a digital assistant, wherein the digital assistant list comprises at least one candidate digital assistant (210); in response to detecting the determination of a target digital assistant, receiving a request for the target digital assistant (220); and in response to receiving the request, providing a response to the request in the interactive interface via the target digital assistant (230).

Description

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

[0001] The present application claims priority to the Chinese patent application No. 202410870520.1, filed on June 30, 2024, entitled “Information processing method, apparatus, device, storage medium, and program product”, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] Example embodiments of the present disclosure generally relate to the field of computers, and in particular, to an information processing method, apparatus, device, storage medium, and program product. BACKGROUND

[0003] With the development of information technology, various terminal devices can provide people with various services in work and life, etc. For example, an application providing a service can be deployed in a terminal device. The terminal device or the application can provide a digital assistant type function to a user to assist the user in using the terminal device or the application. The user can complete diversified operations through various interactions with the digital assistant. SUMMARY

[0004] In a first aspect of the present disclosure, an information processing method is provided. The method comprises: in response to detecting a predetermined mention symbol input by a user in an interaction interface, providing a presentation of a digital assistant list in the interaction interface based on at least one of interaction context information in the interaction interface and at least one historical interaction operation of the user for a digital assistant, the digital assistant list comprising at least one candidate digital assistant; in response to detecting a determination of a target digital assistant, receiving a request for the target digital assistant; and in response to receiving the request, providing a response to the request in the interaction interface with the target digital assistant.

[0005] In a second aspect of the present disclosure, an apparatus for information processing is provided. The apparatus comprises: a list presentation module configured to, in response to detecting a predetermined mention symbol input by a user in an interaction interface, provide a presentation of a digital assistant list in the interaction interface based on at least one of interaction context information in the interaction interface and at least one historical interaction operation of the user for a digital assistant, the digital assistant list comprising at least one candidate digital assistant; a request receiving module configured to, in response to detecting a determination of a target digital assistant, receive a request for the target digital assistant; and a response providing module configured to, in response to receiving the request, provide a response to the request in the interaction interface with the target digital assistant.

[0006] In a third aspect of the 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. The instructions, when executed by the at least one processor, cause the electronic device to perform the method of the first aspect.

[0007] In a fourth aspect of the disclosure, a computer-readable storage medium is provided. The medium has computer-executable instructions stored thereon that, when executed by a processor, implement the method of the first aspect.

[0008] In a fifth aspect of the disclosure, a computer program product is provided. The product includes computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to the first aspect of the disclosure.

[0009] It should be understood that the details described in this section are not intended to limit key or important features of embodiments of the disclosure or limit the scope of the disclosure. Other features of the disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0010] The above and other features, advantages, and aspects of embodiments of the disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings in which:

[0011] FIG. 1 illustrates a schematic diagram of an example environment;

[0012] FIG. 2 illustrates a flowchart of an example method for information processing;

[0013] FIGS. 3A to 3I illustrate example interfaces;

[0014] FIG. 4 illustrates an example of a signaling flow for information processing;

[0015] FIG. 5 illustrates an example of a signaling flow for information processing;

[0016] FIG. 6 illustrates an example structural block diagram of an apparatus for information processing; and

[0017] FIG. 7 illustrates a block diagram of an example electronic device. DETAILED DESCRIPTION

[0018] 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 drawings, it is understood that the present disclosure can be implemented in various forms and should not be interpreted as being limited to the embodiments set forth herein, but rather, these embodiments are provided so as to more completely and thoroughly understand the present disclosure. It is understood that the drawings and embodiments of the present disclosure are for exemplary purposes only and are not intended to limit the scope of protection of the present disclosure.

[0019] In the description of embodiments of the present disclosure, the term "comprising" and its conjugations should be understood to encompass the meaning of "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 can also be included below.

[0020] In this document, unless explicitly stated, performing a step "in response to A" does not mean performing the step immediately after A, but can include one or more intermediate steps.

[0021] It can be understood that the data involved in the technical solutions of the present disclosure (including but not limited to the data itself, the obtaining, use, storage or deletion of the data) should comply with the requirements of relevant laws and regulations and relevant provisions.

[0022] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the type of information involved in the present disclosure, the scope of use, the use scenario, etc. should be informed to the relevant user and the authorization of the relevant user should be obtained by appropriate means, wherein the relevant user can include any type of right subject, such as an individual, an enterprise or a group.

[0023] For example, in response to receiving the active request of the user, a prompt information is sent to the relevant user to explicitly prompt the relevant user that the operation requested to be performed will require the information of the relevant user to be obtained and used, so that the relevant user can voluntarily choose whether to provide the information to the software or hardware such as electronic device, application program, server or storage medium, etc. performing the operation of the technical solutions of the present disclosure according to the prompt information.

[0024] As an optional but not limiting implementation manner, in response to receiving the active request of the relevant user, the manner of sending the prompt information to the relevant user can be, for example, the manner of pop-up window, and the prompt information can be presented in the form of text in the pop-up window. In addition, the pop-up window can also carry selection controls for the user to select "agree" or "disagree" to provide information to the electronic device.

[0025] It can be understood that the above notification and user authorization obtaining process is only illustrative, and does not limit the implementation of the present disclosure, and other ways that meet the relevant laws and regulations can also be applied to the implementation of the present disclosure.

[0026] As used herein, the term “model” can refer to a structure that learns the association between respective inputs and outputs from training data, so that after training is completed, the corresponding output can be generated for a given input. The generation of a model can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes input and provides a corresponding output by using multiple layers of processors. A neural network model is one example of a model based on deep learning. In this document, a “model” can also be referred to as a “machine learning model”, a “learning model”, a “machine learning network” or a “learning network”, which are used interchangeably herein.

[0027] FIG. 1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. In the example environment 100, an application service component 112 and a digital assistant 114 are installed in a client device 110. A user 130 can interact with the application service component 112 and the digital assistant 114 via the client device 110 and / or an attached device of the client device 110.

[0028] In some embodiments, the application service component 112 and the digital assistant 114 can be downloaded and installed in the client device 110. In some embodiments, the application service component 112 and the digital assistant 114 can also be accessed by other means, such as accessed through a webpage, etc. In some embodiments, in the environment 100 of FIG. 1, in response to the application service component 112 being launched, the client device 110 can present an interface 140 of the application service component 112 and the digital assistant 114. The interface 140 can be, for example, an interactive interface of the application service component 112 and the digital assistant 114.

[0029] The application service component 112 includes, but is not limited to, one or more of the following: a chat application component (also referred to as an instant messaging application component), a document application component, an audio and video conference application component, a mail application component, a task application component, a calendar application component, an objective and key result (OKR) application component, etc. It can be understood that although a single application service component is shown in FIG. 1, multiple application service components can be installed on the client device 110. In some embodiments, the application service component 112 can include a multi-functional collaboration platform, such as an office collaboration platform (also referred to as an office suite) that can provide integration of multiple types of service components to facilitate people to carry out office activities, communication activities, etc. In the multi-functional collaboration platform, people can start different service components as needed to complete corresponding information processing, sharing, communication, etc.

[0030] In some embodiments, the digital assistant 114 can be provided by a separate application service component, or can be integrated in a certain application service component 112 capable of providing content entities. The application service component for providing the client interface of the digital assistant can correspond to a single-function application service component or a multi-function collaboration platform, such as an office suite or other collaboration platform capable of integrating multiple components. It can be understood that similar to the application service component, although a single digital assistant is shown in FIG. 1, there can actually be multiple digital assistants.

[0031] In some embodiments, the digital assistant 114 supports the use of plugins. Each plugin is capable of providing one or more functions of an application. Such plugins include, but are not limited to, one or more of the following: a search plugin, a contact plugin, a message plugin, a document plugin, a table plugin, a mail plugin, a calendar plugin, a schedule plugin, a task plugin, and the like.

[0032] The digital assistant 114 is a smart assistant for the user, with intelligent conversation and information processing capabilities. In embodiments of the present disclosure, the digital assistant 114 is used for interaction with the user 130 to assist the user 130 in using the terminal device or the application. In some embodiments, an interaction window with the digital assistant 114 can be presented in the interface 140. In the interaction window, the user 130 is capable of conversing with the digital assistant 114 by inputting natural language text, pictures, audio files, video files, web page files, and the like, to instruct the digital assistant to assist in completing various tasks, including operations on content entities 126.

[0033] In some embodiments, multiple interaction modes of the user 130 with the digital assistant 114 can be provided, and flexible switching between the multiple interaction modes can be provided. In the case that a certain interaction mode is triggered, a corresponding interaction area is presented to facilitate the interaction of the user 130 with the digital assistant 114. The way the user 130 interacts with the digital assistant 114 is different in different interaction modes, so that the interaction needs in different application scenarios can be flexibly adapted.

[0034] In some embodiments, information processing services specific to the user 130 can be provided based on historical interaction information of the user 130 with the digital assistant 114 and / or a data range specific to the user 130. In some embodiments, the historical interaction information of the user 130 interacting with the digital assistant 114 in multiple interaction modes respectively can all be stored in association with the user 130. In this way, in one of the multiple interaction modes (any one or a specified one), the digital assistant 114 can provide services for the user 130 based on the historical interaction information stored in association with the user 130.

[0035] The digital assistant 114 can be invoked or woken up by appropriate means (e.g., a shortcut, a button, or a voice) to present an interaction window with the user 130. The interaction window with the digital assistant 114 can be initiated by selecting the digital assistant 114. The interaction window can include interface elements for information interaction, such as an input box, a message list, a message bubble, and the like. In some embodiments, the digital assistant 114 can be invoked through an entry control or a menu provided in the interface 140, or through input of a preset instruction.

[0036] The interaction window of the digital assistant 114 with the user 130 can include a conversation window, such as a conversation window in an instant messaging application or an instant messaging module of a specific application. In the conversation window, the interaction between the digital assistant 114 and the user 130 can be presented in the form of conversation messages. Alternatively or additionally, the interaction window of the digital assistant 114 with the user 130 can also include other types of windows, such as a window in a floating window mode, in which the user 130 can trigger the digital assistant 114 to perform corresponding operations by inputting instructions, selecting shortcut instructions, and the like.

[0037] In some embodiments, the digital assistant 114 can support an interaction mode of the conversation window, also referred to as a conversation mode. In the interaction mode, a conversation window of the user 130 with the digital assistant 114 is presented, in which the user 130 and the digital assistant 114 interact through conversation messages. In the conversation mode, the digital assistant 114 can perform tasks according to the conversation messages in the conversation window. In the interaction window, the user 130 inputs an interaction message, and the digital assistant 114 provides a reply message in response to the user input. The conversation window with the digital assistant 114 can be initiated by selecting the digital assistant 114. The conversation window can include interface elements for information interaction, such as an input box, a message list, a message bubble, and the like.

[0038] In some embodiments, the client device 110 communicates with the server device 120 to enable provisioning of services of the digital assistant 114 and the business component 125. The client device 110 can be any suitable type of mobile terminal, fixed terminal, or portable terminal including a mobile handset, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a television receiver, a radio broadcast receiver, an e-book device, a game device, or any combination thereof, including accessories and peripherals of such devices, or any combination thereof. In some embodiments, the client device 110 can also be capable of supporting any type of interface for the user (such as "wearable" circuitry, etc.). The server device 120 can be various types of computing systems / servers capable of providing computing capabilities, including but not limited to mainframes, edge computing nodes, computing devices in a cloud environment, etc.

[0039] It should be understood that the structure and function of the various elements in the environment 100 are described for illustrative purposes only and without implying any limitation on the scope of the present disclosure.

[0040] As mentioned previously, a user can accomplish diverse operations through various interactions with digital assistants. Different digital assistants can have different capabilities, and a user can accomplish different operations through interactions with different digital assistants. For example, a user can obtain a recommended dish from a digital assistant with a dish recommendation function through an interaction with the digital assistant, the user can obtain a result of a movie analysis sent by a digital assistant with a movie analysis function through an interaction with the digital assistant, and the like. Conventionally, if a user desires to interact with a digital assistant with a specific function, the user usually needs to manually select a target digital assistant with the function from multiple digital assistants. This affects the efficiency of the user in selecting the target digital assistant. It is desirable to conveniently and quickly recommend a suitable digital assistant to a user.

[0041] In view of this, according to an embodiment of the present disclosure, an improved solution for information processing is provided. According to the solution of the embodiment of the present disclosure, in response to detecting a predetermined mention symbol input by a user in an interaction interface, a presentation of a list of digital assistants is provided in the interaction interface based on at least one of interaction context information in the interaction interface and at least one historical interaction operation of the user for a digital assistant, the list of digital assistants including at least one candidate digital assistant. In response to detecting a determination of a target digital assistant, a request for the target digital assistant is received. In response to receiving the request, a response to the request is provided in the interaction interface via the target digital assistant.

[0042] In this way, the candidate digital assistant can be quickly presented for the user to select based on the interaction context information in the interaction interface and / or the at least one historical interaction operation of the user with the digital assistant. This can facilitate the recommendation of the digital assistant to the user, improve the convenience of the user to select the digital assistant, provide the efficiency of information processing, and improve the user experience of the user and the digital assistant interaction.

[0043] Some example embodiments of the present disclosure will be hereinafter described with continuous reference to the drawings.

[0044] FIG. 2 illustrates a flowchart of an example process 200 for information processing according to some embodiments of the present disclosure. For ease of discussion, the process 200 will be described with reference to the environment 100 of FIG. 1. The process 200 can be implemented at the client device 110 and / or the server device 120. For ease of description, the process 200 will be described with an example that the process 200 is implemented at the server device 120.

[0045] It is noted that if the process 200 is implemented at the client device 110, some operations described with reference to the client device 110 can need the assistance of the server device 120 to be completed. It is noted that the operations performed by the client device 110 can be specifically performed by the relevant application and / or the digital assistant installed on the client device 110.

[0046] At block 210, in response to detecting a predetermined mention symbol input by a user (e.g., the user 130) in an interaction interface, the server device 120 provides a presentation of a list of digital assistants in the interaction interface based on at least one of the interaction context information in the interaction interface and the at least one historical interaction operation of the user with the digital assistant, the list of digital assistants including at least one candidate digital assistant.

[0047] The interaction interface refers to an interface that can receive interaction information from a user and present response information to the user. In some examples, the interaction interface can include interfaces associated with a post (e.g., a region corresponding to the post body, a comment region for the post, etc.) and a conversation window (e.g., a conversation window between the user and other users, a conversation window between the user and a digital assistant, etc.). It can be understood that the interaction interface can also include any other appropriate interface. It is noted that if the interaction interface is a conversation window between the user and a digital assistant, the digital assistant corresponding to the conversation window and the candidate digital assistant in the list of digital assistants can be different digital assistants or the same digital assistant.

[0048] The predetermined mention symbol can be any suitable symbol for mentioning a particular object. In some embodiments, the mention symbol can be, for example, the symbol "@", the symbol " / ", and the like. The interactive interface (e.g., the interface 140) provided by the client device 110 can include, for example, an input box. The client device 110 can send, to the server device 120, an indication indicating that the predetermined mention symbol is detected in the interactive interface in response to receiving the predetermined mention symbol inputted by the user via the input box. The server device 120 can determine that the predetermined mention symbol inputted by the user is detected in the interactive interface in response to receiving the indication. In some embodiments, the interactive interface can also be presented with a mention control corresponding to the predetermined mention symbol. The client device 110 can send, to the server device 120, an indication indicating that the predetermined mention symbol is detected in the interactive interface in response to receiving a triggering operation for the mention control.

[0049] If the interactive interface is an interface associated with a post, the interaction context information in the interactive interface can include, for example, a post published by the user, a post interacted by the user (e.g., a post collected by the user, a post liked by the user, a post commented by the user, and the like), a comment published by the user for the post, a comment on the post published by the user / interactioned by the user by other users / digital assistants, a reply to the comment on the post by the user by other users / digital assistants, and the like.

[0050] If the interactive interface is a conversation window, the interaction context information in the interactive interface can include, for example, a plurality of rounds of conversation in history between the user and other users / digital assistants. It is noted that in some embodiments, the interaction context information can also include the user input inputted by the user currently. For example, the interaction context information can also include the user input received by the client device 110 via the input box. The at least one historical interaction operation by the user for the digital assistant can include a collection behavior by the user for the digital assistant, an interaction operation by the user for the digital assistant, and the like. The interaction operation for the digital assistant can indicate that the digital assistant is interacted by the user historically. The collection behavior or operation refers to associating the digital assistant or application with a particular collection list associated with the user. For example, the collection list is created, liked, or saved by the user. The collection behavior can also be referred to as a like behavior or operation, a save behavior or operation, and the like.

[0051] In some embodiments, the server-side device 120 can select one or more candidate digital assistants from the plurality of candidate digital assistants based on a match between the description information of the plurality of candidate digital assistants and the interaction context information. For example, the server-side device 120 can determine, based on the interaction context information, a target function and / or a target name that a digital assistant to be selected should have. The server-side device 120 can select, from the description information of the plurality of candidate digital assistants, one or more candidate digital assistants that have the target function and / or the target name.

[0052] Alternatively or additionally, in some embodiments, the server-side device 120 can also select, as the one or more candidate digital assistants, one or more digital assistants involved in the at least one historical interaction operation. For example, a digital assistant that is collected by the user, a digital assistant that is interacted with by the user in the past, and the like can be determined as the one or more candidate digital assistants.

[0053] If the one or more candidate digital assistants determined based on the interaction context information and / or the at least one historical interaction operation includes only one candidate digital assistant, the server-side device 120 can directly provide the candidate digital assistant to the user. If the one or more candidate digital assistants determined includes a plurality of candidate digital assistants, in order to facilitate the user to select a digital assistant that the user desires from the plurality of candidate digital assistants, the server-side device 120 can rank the plurality of candidate digital assistants and determine a list of digital assistants based on the ranking result for presentation.

[0054] Referring to FIG. 3A, an example 300A illustrates one example of an interaction interface. The example 300A includes an input box 301 and a mention control 302. A list of digital assistants 310 can be presented in response to receiving a symbol “@” via the input box 301 or in response to receiving a triggering operation on the mention control 302. The one or more candidate digital assistants determined by the server-side device 120 based on the interaction context information and / or the at least one historical interaction operation can be presented in the list of digital assistants 310.

[0055] As to the specific manner of ranking the plurality of candidate digital assistants, in some embodiments, the server-side device 120 can rank the plurality of candidate digital assistants based on priority, and the priority of the one or more candidate digital assistants determined based on the at least one historical interaction operation can be higher than the priority of the one or more candidate digital assistants determined based on the interaction context information. That is, the one or more candidate digital assistants determined based on the at least one historical interaction operation can be ranked before the one or more candidate digital assistants determined based on the interaction context information.

[0056] Alternatively or additionally, in some embodiments, the service-side device 120 can also classify the one or more candidate digital assistants determined based on the interaction context information and the one or more candidate digital assistants determined based on the at least one historical interaction operation as different types of candidate digital assistants. The service-side device 120 can also rank the one or more candidate digital assistants of each type separately.

[0057] As to the specific manner of selecting a digital assistant for each type, the service-side device 120 may, for example, rank the candidate digital assistants of each type based on the priority of the candidate digital assistants of the type. Illustratively, as to the one or more candidate digital assistants determined based on the interaction context information, the service-side device 120 can determine that the priority of a candidate digital assistant determined based on interaction context information corresponding to a time closer to the current time is higher than the priority of a candidate digital assistant determined based on interaction context information corresponding to a time farther from the current time. For example, the service-side device 120 can rank the one or more candidate digital assistants determined based on the interaction context information in descending order based on the corresponding priority, with the candidate digital assistant closer to the top in the ranking result corresponding to interaction context information corresponding to a time closer to the current time.

[0058] Illustratively, as to the one or more candidate digital assistants determined based on the at least one historical interaction operation, the service-side device 120 can determine the priority of the corresponding candidate digital assistant based on the operation type of the historical interaction operation. The priority of a candidate digital assistant determined based on a collection behavior can be higher than the priority of a candidate digital assistant determined based on an interaction operation. The service-side device 120 can rank the one or more candidate digital assistants determined based on the at least one historical interaction operation in descending order based on the corresponding priority, with the candidate digital assistant closer to the top in the ranking result corresponding to a historical interaction operation such as a collection behavior, and the candidate digital assistant closer to the bottom in the ranking result corresponding to a historical interaction operation such as an interaction operation.

[0059] In some embodiments, the service-side device 120 can determine a list of digital assistants based on the respective recommendation scores of the at least one candidate digital assistant. The candidate digital assistants here can include different digital assistants from the candidate digital assistants determined based on the interaction context information in the interaction interface and / or the at least one historical interaction operation of the user with respect to the digital assistant. The recommendation score of each digital assistant can be determined based on the number or frequency of use within a period of time (which can be the number or frequency of use of the digital assistant by multiple users within a period of time), the number or frequency of interactions with the user (which can be the number or frequency of interactions with multiple users), the degree of matching between the digital assistant and a popular topic, and the like. For example, the recommendation score of a digital assistant used by a large number of users within a month can be higher.

[0060] In this case, the server device 120 can determine the list of digital assistants based on the interaction context information in the interaction interface, the at least one historical interaction operation of the user for the digital assistant, and the respective recommendation scores of the candidate digital assistants. The list of digital assistants thus determined can include the candidate digital assistants determined based on the interaction context information, the candidate digital assistants interacted by the user historically, and the candidate digital assistants with higher respective recommendation scores. The candidate digital assistants interacted by the user historically can have a higher priority than the candidate digital assistants determined based on the interaction context information, and the candidate digital assistants determined based on the interaction context information can have a higher priority than the candidate digital assistants with higher respective recommendation scores.

[0061] In some embodiments, the server device 120 can score each candidate digital assistant, and the size of the score can indicate the respective priority. It can be understood that the higher the respective priority of a candidate digital assistant, the larger the score. The server device 120 may, for example, obtain a threshold score, and only present in the list of digital assistants the candidate digital assistants with a score higher than the threshold score.

[0062] At block 220, the server device 120 receives a request for the target digital assistant in response to detecting the determination of the target digital assistant.

[0063] In some embodiments, the server device 120 can send the list of digital assistants to the client device 110 to let the client device 110 present the list of digital assistants to the user. The client device 110 can determine a candidate digital assistant in the list of digital assistants as the target digital assistant in response to receiving a selection operation of the user on the candidate digital assistant (i.e., the client device 110 detects the determination of the target digital assistant). The client device 110 can then send a corresponding indication to the server device 120 to inform the server device 120 that the determination of the target digital assistant has been detected.

[0064] In some embodiments, the server device 120 can also determine the target digital assistant directly based on the user input including the specific name / description information of the digital assistant (i.e., the user input can specify a certain digital assistant) in response to receiving the user input. For example, if the text “@digital assistant A” is received via the input box, the server device 120 can determine digital assistant A as the target digital assistant.

[0065] The received request for the target digital assistant can include content in any appropriate format (e.g., picture, voice, text, video, audio, image set, file, etc.). The format can depend on the data modality or limitation for the request in the specific application scenario.

[0066] At block 230, the server device 120 provides, in response to receiving the request, a response to the request in the interaction interface with the target digital assistant.

[0067] In some embodiments, the client device 110 can trigger the server device 120 to determine the response to the request based on the configuration information of the target digital assistant and the interaction context information, and provide the response to the request in the interaction interface with the target digital assistant. The request can be considered as a question, and the response can be considered as an answer to the question. For example, the configuration information can indicate the configuration, rules, version, etc. of the target digital assistant to generate the response. If the target digital assistant is configured to determine the response by means of a specific machine learning model, the target digital assistant can indicate the machine learning model and a prompt input for the machine learning model. This machine learning model can be based on any appropriate model structure, including but not limited to a Transformer model, a convolutional neural network (CNN), a recurrent neural network (RNN), a deep neural network (DNN), etc. In some embodiments, the machine learning model can be based on a language model (LM). A language model can have the ability to answer questions by learning from a large amount of corpus. The machine learning model can also be based on other appropriate models.

[0068] Taking the example that the target digital assistant determines the response by means of a machine learning model, the server device 120 can determine, based on the configuration information of the target digital assistant, a machine learning model for generating the response and a prompt template for the prompt input of the machine learning model. The server device 120 can generate the prompt input for the machine learning model, for example, by filling at least the request into the prompt template. In some embodiments, in order to improve the accuracy of generating the response, the server device 120 can also generate the prompt input for the machine learning model by filling the interaction context information and the request into the prompt template.

[0069] The server device 120 can provide the prompt input to the machine learning model to obtain the response to the request from the machine learning model. The server device 120 can send the response to the client device 110. If the interaction interface is an interface associated with a post, the client device 110 can provide the response in the interaction interface in the form of a comment from the target digital assistant. If the interaction interface is a conversation window, the client device 110 can provide the response in the form of a conversation message from the target digital assistant.

[0070] As to the specific manner of providing the response, in some embodiments, the server device 120 can receive the individual segments of the response from the machine learning model and cache one or more of the received segments of the response. Illustratively, the response generated by the machine learning model can be a response in textual form, and the machine learning model can generate the response word by word or character by character, and the server device 120 can receive the response from the machine learning model word by word or character by character as well.

[0071] The server device 120 may, for example, determine that a segment of the response has been received in response to receiving a predetermined number of texts. For example, the server device 120 may, in response to receiving 10 texts, determine that a segment of the response has been received. Alternatively or additionally, the server device 120 may, in response to receiving a complete sentence or a complete paragraph, determine that a segment of the response has been received.

[0072] The server device 120 may, in response to receiving a segment of the response, cache the segment of the response immediately. The server device 120 may, in response to receiving a predetermined number of segments of the response, cache the segments of the response together. The server device 120 may, for example, cache at least one segment of the response in a database. The database may be a database specifically for caching responses, or a general-purpose database.

[0073] The server device 120 may, in turn, in response to detecting that the first client device is presenting the interactive interface, send the cached segments of the response to the at least one client device for presentation in the interactive interface. The server device 120 may, for example, send the cached segments of the response to the at least one client device one by one in the order in which the segments were received. The at least one client device may, in accordance with the order in which the segments were received, present the response in a streaming manner.

[0074] It should be noted that the first client device can be the client device that received the request. For example, if the interactive interface is a chat window, the server device 120 may, in response to receiving the request from the user at the client device 110, send the response to the client device 110 to provide the user with the response to the request. In this case, the server device 120 may send the cached segments to the client device 110 only.

[0075] The first client device can also be different from the client device that received the request. For example, if the interaction interface is an interface associated with a post, the server device 120 can receive a comment on the post from the user at the client device 110 and determine the comment as the request from the user. The response to the request provided by the server device 120 to the user can be, for example, a reply to the request. Since the post can be public, any user can view the interaction interface, and thus the comment on the post and the reply to the comment can be public. If other users view the interaction interface, the server device 120 can provide the response to other client devices corresponding to the other users. In this case, the server device 120 needs to send the cached segments to all client devices corresponding to the users who view the comment.

[0076] Thus, during the generation of the response, the server device 120 does not need to wait for the generation of the entire response to provide the response to the user, and the server device 120 can cache the response in segments and provide the response to the user in a streaming manner, which can improve the efficiency of the user obtaining the response.

[0077] In some embodiments, the server device 120 can also determine that the generation of the response is not complete in response to detecting that the second client device requests to present the interaction interface. It can be understood that, in the case where the generation of the response is not complete, since the server device 120 provides the response in a streaming manner, the response provided in the interaction interface is only part of the entire response, and the client device that presents the interaction interface cannot provide the complete response to the user. The second client device can be a client device corresponding to a user who re-enters the interaction interface after exiting the interaction interface halfway, or a client device corresponding to a user who first enters the interaction interface during the generation of the response by the digital assistant.

[0078] The server device 120 can send the cached segments of the response to the second client device for presentation. For example, if the response of 3 segments has been cached, the server device 120 can provide the response of the 3 segments to the client device at a time. The client device can provide the response of the 3 segments to the user together. The server device 120 can also send another segment of the response to the second client device in response to receiving the other segment of the response from the machine learning model. That is, the server device 120 can also continue to receive new segments and cache the new segments. The server device 120 can continue to provide the new segments to the client device one by one. In this case, the server device 120 can provide the cached segments at a time and provide the new segments in a streaming manner.

[0079] Thus, during the generation of the response, the user who exits the interaction interface halfway and the user who first accesses the interaction interface can directly see the entire response that has been generated and can continue to obtain the response generated subsequently in a streaming manner.

[0080] Referring to FIGS. 3B-3I, examples 300B-300I illustrate a plurality of examples of the interactive interface. Example 300B includes region 320 and region 330. Region 330 presents content of a certain document, and region 320 can be used to present a name of the document and at least one operation control (e.g., a like control, a favorite control, a forward control, etc.) for the document. It can be understood that the content presented at region 330 can also be content of a web page, content of a post body, etc., and region 320 can be used to present a title, a name, etc. of the content presented at region 330. Region 330 can include input box 331, for example. A user can post a comment for the content in region 330 via input box 331, for example. Example 300B can also include input box 342 and example 344. A user can also post a comment for the content in region 330 via input box 342, for example. Example 344 can be used to show examples of comments that a user can input, for example.

[0081] Example 300B can also include region 350. Region 350 can be used to present at least one post for the content in region 330, for example. Region 350 includes post control 351 and refresh control 352. A user can post a post by triggering post control 351, and can refresh the at least one post presented in region 350 by triggering refresh control 352. Server device 120 can present example 300C in response to receiving a selection operation for post 353 in region 350, for example. Example 300C includes region 360 and region 364. Region 360 can be a region corresponding to a post body, for example, and region 364 can be a comment region for the post, for example. Example 300C includes return control 361, and server device 120 can return to present the interface shown in example 300B in response to receiving a triggering operation for return control 361.

[0082] Region 360 can present the body 362 of the post and an input box 363 for the body 362. The server-side device 120 may, for example, receive a comment for the body 362 via the input box 363. Region 360 can present at least one comment for the post and a reply control for each comment. Referring to FIG. 3D, the server-side device 120 may, for example, in response to receiving a triggering operation of the reply control 372 for the comment 371, determine to receive a comment for the comment 371. The server-side device 120 may, for example, provide an input box 373 for the comment 371 and receive a comment for the comment 371 via the input box 373. The server-side device 120 can provide a cancel control 374 and a send control 375 in association with the input box 373. The server-side device 120 may, in response to receiving a selection operation for the cancel control 374, not publish the comment received via the input box 373. The server-side device 120 may, in response to receiving a selection operation for the send control 375, publish the comment received via the input box 373. This comment will be presented in association with the comment 371.

[0083] In some embodiments, as shown in FIG. 3C and FIG. 3E, the server-side device 120 may, in response to receiving a triggering operation of the input box 363 in the example 300C, present the example 300E. The size of the input box 363 may, for example, increase as the user inputs more comment content until reaching a predetermined size. The server-side device 120 can provide a cancel control 365 and a send control 366 in association with the input box 363. The server-side device 120 may, in response to receiving a selection operation for the cancel control 365, not publish the comment received via the input box 363. The server-side device 120 may, in response to receiving a selection operation for the send control 366, publish the comment received via the input box 363. This comment may, for example, be presented in the region 364. As shown in FIG. 3F, the server-side device 120 can present the comment 381 from the user in the comment region.

[0084] Since the comment 381 mentions the digital assistant A, the server-side device 120 can determine the digital assistant A as the target digital assistant. The server-side device 120 may, for example, utilize the digital assistant A to provide a response for the comment 381 (i.e., a reply for the comment 381). In some embodiments, in the case that a paragraph of the response is not obtained, the server-side device 120 can present a prompt message for prompting the user that the response is currently being obtained. The server-side device 120 may, for example, provide the prompt message via the digital assistant A. The server-side device 120 can provide the interface shown in the example 300G, in which the server-side device 120 can provide the prompt message (i.e., the text "Content generating…") in the comment 382 from the digital assistant A for the comment 381.

[0085] Further, in response to obtaining the one or more segments of the response, the server-side device 120 can stream the segments of the response. As shown in FIG. 3H, in the example 300H, the server-side device 120 can stream the segments of the response in the comment 382 from the digital assistant A. The server-side device 120 can present the interface shown in the example 300I in response to obtaining and caching all segments of the response. In the example 300I, the server-side device 120 can present the complete response in the comment 382.

[0086] FIG. 4 illustrates an example of a signaling flow 400 of information processing according to some embodiments of the present disclosure. The signaling flow 400 involves the client-side device 110, the server-side device 120, a machine learning model 401, and a database 402.

[0087] The client-side device 110 can receive (411) a user input in an interactive interface and send (412) the user input to the server-side device 120. The server-side device 120 can send (413) a request to the database 402 indicating to obtain the interaction context information of the user in the interactive interface. The database 413 can return (414) the interaction context information of the user in the interactive interface to the server-side device 120 based on the request.

[0088] The server-side device 120 can determine at least one candidate digital assistant for the user, for example, based on the interaction context information. The server-side device 120 can determine the at least one candidate digital assistant in any suitable manner. In some embodiments, the server-side device 120 can construct (415) a prompt input for the machine learning model 401 based on the interaction context information. The server-side device 120 can provide (416) the prompt input to the machine learning model 401. The machine learning model 401 can determine the at least one candidate digital assistant, for example, based on the prompt input. The server-side device 120 can obtain (417) a model output from the machine learning model 401, which can indicate a recommendation of the at least one candidate digital assistant. The model output can include, for example, a name, description information, an identifier, a number, or the like of the at least one candidate digital assistant.

[0089] The server-side device 120 can also send a request to the database 402 indicating to obtain (418) the at least one candidate digital assistant based on at least one historical interaction of the user with digital assistants, to obtain (419) the at least one candidate digital assistant from the database 402. It is noted that the server-side device 120 can perform obtaining the at least one candidate digital assistant from the machine learning model 401 and obtaining the at least one candidate digital assistant from the database 402 together, or can obtain the at least one candidate digital assistant from only the machine learning model 401 or only the database 402.

[0090] The server device 120 can rank the at least one candidate digital assistant based on the priority of each candidate operation assistant (420). The server device 120 can determine a list of digital assistants based on the ranking result, and return (421) the list of digital assistants to the client device 110. The client device 110 can in turn present the list of digital assistants to the user, and receive (422) the determination of the target digital assistant by the user.

[0091] FIG. 5 illustrates an example of a signaling flow 500 of information processing according to some other embodiments of the present disclosure. The signaling flow 500 can likewise involve the client device 110, the server device 120, the machine learning model 401, and the database 402.

[0092] The client device 110 can send (501) the request of the user input received in the interaction interface to the server device 120, for example. The server device 120 can obtain and parse (502) the context information (e.g., historical dialogue information) of the request of the user. The server device 120 can send (503) a request to the database 402 indicating to obtain the configuration information of the target digital assistant. The database 402 can return (504) the configuration information of the target digital assistant to the server device 120 based on the request.

[0093] If the configuration information indicates that the target digital assistant is to generate a response with the aid of a machine learning model (e.g., the machine learning model 401), the server device 120 can construct (505) a prompt word input for the machine learning model 401 based on the request and the context information. The server device 120 can send (506) the prompt word input to the machine learning model 401 and obtain (507) the response generated by the machine learning model 401 from the machine learning model 401. The machine learning model 401 can generate the response word by word or character by character, for example, and accordingly, the server device 120 can obtain the response from the machine learning model 401 word by word or character by character.

[0094] The server device 120 can generate (508) segments of the response based on the received content. The server device 120 can send the segments of the response to the database 402 to cache (509) the segments of the response, for example. The server device 120 can further obtain (510) the cached segments from the database 402 and send (511) the cached segments to the client device 110. The client device 110 can provide the received segments to the client device 110 to stream (512) the response to the user in the interaction interface by the client device 110. That is, through the caching mechanism, the effect of streaming can be achieved from the perspective of the client device.

[0095] Although it is shown in FIG. 5 that the response is provided to the client device that initiates the request, in some embodiments, the interactive interface that receives the request for the target assistant and the response can also be accessed by other client devices. For example, if the interactive interface is a public post page, when the first user initiates the request via the associated first client device, if other client devices are accessing the current interactive interface when the response to the request is being generated, the server device 120 can also return the content of the response to the other client devices in the similar procedure as described above, segment by segment. In this way, the streaming presentation effect of the response can also be achieved on the other client devices.

[0096] In some embodiments, in the re-entry after exit scenario, after the client device 110 exits the interactive interface and then re-enters the interactive interface, the client device 110 can send (521) a request to the server device 120 indicating that the client device 110 exits the interactive interface and then re-enters the interactive interface. The server device 120 can determine (522) that there is a response being generated (i.e., the generation of the response is not completed) in response to the request. The server device 120 can send (523) the cached segments of the response to the client device 110 to enable the client device 110 to present the cached segments to the user. The server device 120 can continue to send (524) a request to the database 402 indicating to obtain the latest cached segments (i.e., continue to read the cache). The database 402 can send (525) the newly cached segments to the server device 120 based on the request (i.e., return the subsequent cached segments to the server device 120). The server device 120 can return (526) the subsequent cached segments to the client device 110. The client device 110 can stream (527) the subsequent segments of the response to the user after the previously presented cached segments.

[0097] That is, in the re-entry after exit scenario, the client device 110 can first see the part of the response that has been uploaded when accessing the interactive interface, and the subsequent content can still be streamed on the interactive interface. Similarly, the above-described re-entry after exit scenario also applies to other client devices corresponding to non-request initiators.

[0098] In summary, according to the embodiments of the present disclosure, at least one candidate digital assistant for a user can be determined based on the interaction context information of the user in the interactive interface and / or at least one historical interaction operation of the user for the digital assistant, and a response can be provided to the user via the target digital assistant based on the selection of the target digital assistant by the user. The digital assistant can be conveniently recommended to the user, the convenience of the user to select the digital assistant can be improved, the efficiency of information processing can be provided, and the user experience of the user and the digital assistant interaction can be improved.

[0099] Embodiments of the present disclosure also provide a corresponding apparatus for implementing the above method or process. FIG. 6 shows an exemplary structural block diagram of an apparatus 600 for information processing according to some embodiments of the present disclosure. The apparatus 600 can be implemented as or included in the client device 110 and / or the server device 120. Various modules / components in the apparatus 600 can be implemented by hardware, software, firmware, or any combination thereof.

[0100] As shown in FIG. 6, the apparatus 600 includes a list presentation module 610 configured to, in response to detecting a predetermined mention symbol of a user input in an interactive interface, provide a presentation of a digital assistant list in the interactive interface based on at least one of the interaction context information in the interactive interface and at least one historical interaction operation of the user for a digital assistant, the digital assistant list including at least one candidate digital assistant. The apparatus 600 further includes a request receiving module 620 configured to, in response to detecting a determination of a target digital assistant, receive a request for the target digital assistant. The apparatus 600 further includes a response providing module 630 configured to, in response to receiving the request, provide a response for the request in the interactive interface with the target digital assistant.

[0101] In some embodiments, the list presentation module 610 includes: an execution module configured to perform at least one of the following: selecting one or more candidate digital assistants from a plurality of candidate digital assistants based on a match between description information of the plurality of candidate digital assistants and the interaction context information, or selecting one or more digital assistants involved in the at least one historical interaction operation as the one or more candidate digital assistants; an ordering module configured to order the selected candidate digital assistants; and a presentation module configured to determine the digital assistant list for presentation based on a result of the ordering.

[0102] In some embodiments, the ordering module is further configured to order the selected candidate digital assistants based on a priority corresponding to the interaction context information and respective priorities of the at least one historical interaction operation.

[0103] In some embodiments, the list presentation module 610 is further configured to determine the digital assistant list based on respective recommendation scores of the at least one candidate digital assistant.

[0104] In some embodiments, the at least one historical interaction operation includes at least one of the following: a collection behavior for a digital assistant, an interaction operation for a digital assistant.

[0105] In some embodiments, the interactive interface includes at least one of the following: an area corresponding to a post body, a comment area for a post, a conversation window between the user and other users, a conversation window between the user and a digital assistant.

[0106] In some embodiments, the response providing module 630 includes a response determining module configured to determine the response to the request based on the configuration information of the target digital assistant and the interaction context information, and a first response providing module configured to provide the response to the request in the interaction interface with the target digital assistant.

[0107] In some embodiments, the response providing module 630 includes a response generating module configured to receive individual segments of the response from a machine learning model configured to generate the response based on at least the request, a response caching module configured to cache one or more segments of the received response, and a response sending module configured to send the cached segments of the response to the at least one client device for presentation in the interaction interface in response to detecting that the first client device is rendering the interaction interface.

[0108] In some embodiments, the response providing module 630 further includes a determining module configured to determine that generation of the response is not complete in response to detecting that the second client device requests to render the interaction interface, a cached sending module configured to send the cached segments of the response to the second client device for presentation, and a segment sending module configured to send additional segments of the response to the second client device in response to receiving the additional segments from the machine learning model.

[0109] The units and / or modules included in the apparatus 600 can be implemented utilizing a variety of means, including software, hardware, firmware, or any combination of these. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, e.g., machine executable instructions stored on a machine readable medium. In addition to or alternatively, some or all of the units and / or modules in the apparatus 600 can be implemented at least partially by one or more hardware logic components. As an example and not by way of limitation, example types of hardware logic components include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SOCs), complex programmable logic devices (CPLDs), etc.

[0110] It will be appreciated that one or more steps in the above methods can be performed by an appropriate electronic device or combination of electronic devices. Such electronic devices or combinations of electronic devices can include, for example, the client device 110 and / or the server device 120 in FIG. 1.

[0111] FIG. 7 illustrates a block diagram of an electronic device 700 in which one or more embodiments of the disclosure can be implemented. It should be understood that the electronic device 700 illustrated in FIG. 7 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 700 illustrated in FIG. 7 can be used to implement the client device 110 and / or the server device 120 of FIG. 1.

[0112] As illustrated in FIG. 7, the electronic device 700 is in the form of a general electronic device. Components of the electronic device 700 can include, but are not limited to, one or more processors 710 or processing units, a memory 720, a storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. The processor 710 can be a real or virtual processor and is capable of performing various processing according to programs stored in the memory 720. In a multi-processor system, multiple processors perform computer-executable instructions in parallel to improve parallel processing capability of the electronic device 700.

[0113] The electronic device 700 typically includes a number of computer storage media. Such media can be any available media that is accessible by the electronic device 700 and includes both volatile and non-volatile media, removable and non-removable media. The memory 720 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory), or some combination thereof. The storage device 730 can be a removable or non-removable media and can include machine-readable media such as a flash drive, a magnetic disk drive, or any other media that can be used to store information and / or data and that can be accessed by the electronic device 700.

[0114] The electronic device 700 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 7, a disk drive for reading from or writing to a removable, non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable, non-volatile optical disk (e.g., a CD-ROM) can be provided. In such instances, each drive can be connected to the bus (not shown) by one or more data media interfaces. The memory 720 can include a computer program product 725 having one or more program modules configured to carry out the various methods or actions of the various embodiments of the present disclosure.

[0115] The communication unit 740 enables communication with other electronic devices over a communication medium. Additionally, the functionality of the components of the electronic device 700 can be implemented in a single computing cluster or a plurality of computer machines capable of communicating with one another over a communication connection. As such, the electronic device 700 can operate in a networked environment using logical connections to one or more other servers, a network personal computer (PC) or another network node.

[0116] The input device 750 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. The output device 760 can be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 700 can also communicate with one or more external devices (not shown), such as a storage device, a display device, etc., through the communication unit 740, as needed, one or more devices that enable a user to interact with the electronic device 700, or any devices (e.g., a network card, a modem, etc.) that enable the electronic device 700 to communicate with one or more other electronic devices. Such communication can be carried out via an input / output (I / O) interface (not shown).

[0117] According to an example implementation of the present disclosure, a computer readable storage medium is provided, having computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to perform operations to implement the method described above. According to an example 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, where the computer executable instructions are executed by a processor to perform operations to implement the method described above.

[0118] Various aspects of the disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, and computer program products according to implementations of the disclosure. It will 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.

[0119] 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.

[0120] 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.

[0121] 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, as newer, 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.

[0122] Implementations of this disclosure have been described above. The foregoing description is merely illustrative and not exhaustive, nor is it 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 processing, comprising: in response to detecting a predetermined mention symbol of a user input in an interactive interface, providing a presentation of a digital assistant list in the interactive interface based on at least one of interaction context information in the interactive interface and at least one historical interaction operation of the user with a digital assistant, the digital assistant list comprising at least one candidate digital assistant; in response to detecting a determination of a target digital assistant, receiving a request for the target digital assistant; and in response to receiving the request, providing a response to the request in the interactive interface via the target digital assistant.

2. The method of claim 1, wherein providing a presentation of a digital assistant list in the interactive interface comprises: performing at least one of: selecting one or more candidate digital assistants from the plurality of candidate digital assistants based on a match between description information of the at least one candidate digital assistant and the interaction context information, or selecting one or more digital assistants involved in the at least one historical interaction operation as the at least one candidate digital assistant; ranking the selected at least one candidate digital assistant; and determining the digital assistant list for presentation based on a result of the ranking.

3. The method of claim 2, wherein determining the digital assistant list for presentation by ranking the selected candidate digital assistants comprises: ranking the selected at least one candidate digital assistant based on a priority corresponding to the interaction context information and a respective priority of the at least one historical interaction operation.

4. The method of claim 1, wherein providing a presentation of a digital assistant list in the interactive interface comprises: determining the digital assistant list further based on a respective recommendation score of the at least one candidate digital assistant.

5. The method of claim 1, wherein the at least one historical interaction operation comprises at least one of a favorite behavior of a digital assistant or an interaction operation of a digital assistant.

6. The method of claim 1, wherein the interactive interface comprises at least one of: a region corresponding to a post body, a comment region for a post, a conversation window of the user with other users, or a conversation window of the user with a digital assistant.

7. The method of claim 1, wherein providing a response to the request in the interactive interface with the target digital assistant comprises: determining the response to the request based on configuration information of the target digital assistant and the interaction context information; and providing the response to the request in the interactive interface with the target digital assistant.

8. The method of claim 1, wherein providing a response to the request in the interactive interface with the target digital assistant comprises: receiving respective segments of the response from a machine learning model configured to generate the response based on at least the request; caching one or more segments of the received response; and providing the response to the request in the interactive interface with the target digital assistant. ​ ​ ​ in response to detecting that the first client device is rendering the interactive interface, sending the cached segments of the response to the at least one client device for rendering in the interactive interface.

9. The method of claim 8, wherein providing the response to the request in the interactive interface via the target digital assistant further comprises: in response to detecting that a second client device requests to render the interactive interface, determining that generation of the response is not complete; sending the cached segments of the response to the second client device for rendering; and in response to receiving additional segments of the response from the machine learning model, sending the additional segments to the second client device.

10. An apparatus for information processing, comprising: a list rendering module configured to, in response to detecting a predetermined mention symbol of a user input in an interactive interface, provide a rendering of a list of digital assistants in the interactive interface based on at least one of interaction context information in the interactive interface and at least one historical interaction operation of the user for a digital assistant, the list of digital assistants including at least one candidate digital assistant; a request receiving module configured to, in response to detecting a determination of a target digital assistant, receive a request for the target digital assistant; and a response providing module configured to, in response to receiving the request, provide a response to the request in the interactive interface via the target digital assistant.

11. An electronic device, comprising: at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions, when executed by the at least one processor, cause the electronic device to perform the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having computer-executable instructions stored thereon that are operable to be executed by a processor to implement the method according to any one of claims 1 to 9.

13. A computer program product comprising computer-executable instructions, wherein the computer-executable instructions, when executed by a processor, implement the method according to any one of claims 1 to 9.

Images