Methods, apparatus, devices, and storage media for session interaction
The method and apparatus enable digital assistants to generate and present reply messages based on contextual information from multiple users, addressing the limitation of traditional systems by facilitating conversational discussions in group chats.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- BEIJING ZITIAO NETWORK TECH CO LTD
- Filing Date
- 2024-11-08
- Publication Date
- 2026-05-19
AI Technical Summary
Existing digital assistants in group chat scenarios are limited in their ability to provide replies based on the context of multiple users, failing to facilitate conversational discussions on a given topic.
A method and apparatus for session interaction that involves receiving a session message from a user, generating a reply message based on contextual information related to the topic, and presenting it within the session, enabling replies based on the context of multiple users and facilitating conversational discussions.
Enhances interaction flexibility by allowing digital assistants to respond to multiple users' questions within a given topic, improving collaboration efficiency in group chat scenarios.
Smart Images

Figure 2026516138000001_ABST
Abstract
Description
Technical Field
[0001] (Cross - reference to Related Applications) This application claims the priority of a Chinese patent application filed on November 8, 2023, with the invention title "Method, Apparatus, Device, and Storage Medium for Session Interaction" and application number 202311482320.0. This application further claims the priority of a Chinese patent application filed on November 22, 2023, with the invention title "Method, Apparatus, Device, and Storage Medium for Session Interaction" and application number 202311570257.6. All of the content of the above applications is incorporated herein by reference.
[0002] (Field of the Invention) Exemplary embodiments of the present disclosure generally relate to the field of computers, and particularly to methods, apparatuses, devices, and computer - readable storage media for session interaction.
Background Art
[0003] With the development of information technology, various terminal devices can provide people with various services in aspects such as work and life. The terminal device may be equipped with applications that provide services. The terminal device presents corresponding content through the user interface of the application, realizes the interaction with the user, and meets various needs of the user. Therefore, a rich application interaction interface is an important means to enhance the user experience. The terminal device or application can provide digital assistant - based functions to assist the user in using the terminal device or application. How to improve the interaction flexibility between the user and the digital assistant is a technical problem that needs to be explored currently. In addition, the user may need to use the digital assistant in different sessions.
Summary of the Invention
[0004] A first aspect of this disclosure provides a method for session interaction. This method includes receiving a first session message from a first user to a digital assistant in a first topic of a group chat session including at least one user and a digital assistant; generating a first reply message for the digital assistant to the first session message based on contextual information related to the first topic; and presenting the first reply message for the digital assistant in the first topic.
[0005] A second aspect of the present disclosure provides a device for session interaction. The device comprises a receiving module configured to receive a first session message from a first user to a digital assistant in a first topic of a group chat session including at least one user and a digital assistant; a generating module configured to generate a first reply message for the digital assistant to the first session message based on contextual information related to the first topic; and a presenting module configured to present the first reply message for the digital assistant in the first topic.
[0006] A third aspect of the present disclosure provides an electronic device comprising at least one processing unit and at least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions to be executed by the at least one processing unit. When instructions are executed by the at least one processing unit, the electronic device is made to perform the method of the first aspect.
[0007] A fourth aspect of this disclosure provides a computer-readable storage medium, the medium storing a computer program, and when the computer program is executed by a processor, the method of the first aspect is realized.
[0008] A fifth aspect of this disclosure provides a method for session interaction. The method includes, in a session comprising at least one user and a digital assistant, receiving a first session message from a first user to a digital assistant; determining contextual information associated with the first session message depending on the trigger mode of the first session message; generating a first reply message for the digital assistant to the first session message based on the contextual information; and presenting the first reply message depending on the presentation mode associated with the trigger mode.
[0009] A sixth aspect of the present disclosure provides an apparatus for session interaction. The apparatus comprises: a receiving module configured to receive a first session message from a first user to a digital assistant in a session including at least one user and a digital assistant; a context information determination module configured to determine context information associated with the first session message in accordance with the trigger mode of the first session message; a first reply message generation module configured to generate a first reply message for the digital assistant to the first session message based on the context information; and a presentation module configured to present the first reply message in accordance with the presentation mode associated with the trigger scheme.
[0010] A seventh aspect of this disclosure provides an electronic device comprising at least one processing unit and at least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions to be executed by the at least one processing unit. When instructions are executed by the at least one processing unit, the electronic device is made to perform the method of the fifth aspect.
[0011] According to an eighth aspect of this disclosure, a computer-readable storage medium is provided. The medium stores a computer program, and when the computer program is executed by a processor, the method of the fifth aspect is realized.
[0012] The contents described in this section are not intended to limit any essential or important features of the embodiments of this disclosure, nor to limit the scope of this disclosure. It should be understood that other features of this disclosure are made clearer by the following descriptions. [Brief explanation of the drawing]
[0013] The above and other features, advantages and aspects of each embodiment of this disclosure will become more apparent by referring to the following detailed description in conjunction with the drawings. In the drawings, the same or similar reference numerals represent the same or similar elements. [Figure 1] A schematic diagram of an exemplary environment capable of realizing the embodiments of this disclosure is shown. [Figure 2] A flowchart illustrating an exemplary process for session interaction according to several embodiments of this disclosure is shown. [Figure 3A] A schematic diagram of an exemplary session interaction interface according to some embodiments of this disclosure is shown. [Figure 3B] A schematic diagram of an exemplary session interaction interface according to some embodiments of this disclosure is shown. [Figure 3C] A schematic diagram of an exemplary session interaction interface according to some embodiments of this disclosure is shown. [Figure 3D] A schematic diagram of an exemplary session interaction interface according to some embodiments of this disclosure is shown. [Figure 3E] A schematic diagram of an exemplary session interaction interface according to some embodiments of this disclosure is shown. [Figure 3F] A schematic diagram of an exemplary session interaction interface according to some embodiments of this disclosure is shown. [Figure 4] A flowchart of the process for session interaction according to some embodiments of this disclosure is shown. [Figure 5] A schematic structural block diagram of a device for session interaction according to several embodiments of this disclosure is shown. [Figure 6] A flowchart of the process for session interaction according to some embodiments of this disclosure is shown. [Figure 7] A schematic structural block diagram of a device for session interaction according to several embodiments of this disclosure is shown. [Figure 8] A block diagram of an electronic device capable of realizing one or more embodiments of the present disclosure is shown. [Modes for carrying out the invention]
[0014] The embodiments of this disclosure will be described in more detail below with reference to the drawings. While the drawings show several embodiments of this disclosure, it should be understood that this disclosure can be realized in various forms and should not be construed as being limited to the embodiments described herein. Rather, these embodiments are provided to provide a clearer and more complete understanding of this disclosure. It should be understood that the drawings and embodiments of this disclosure are illustrative only and are not intended to limit the scope of protection of this disclosure.
[0015] In the descriptions of the embodiments of this disclosure, the term “including” and similar terms should be understood as non-restrictive “including,” i.e., “including, but not limited to.” The term “based on” should be understood as “based at least in part.” The term “one embodiment” or “this embodiment” should be understood as “at least one embodiment.” The term “several embodiments” should be understood as “at least several embodiments.” The following may include other explicit and implicit definitions.
[0016] Unless otherwise specified in this specification, performing one step "in response to A" does not mean immediately performing this step after "A", and may include one or more intermediate steps.
[0017] It should be understood that the data related to the present technical solution (including but not limited to the data itself, acquisition, use, storage or deletion of the data) should comply with the requirements of relevant laws, regulations and related provisions.
[0018] Before using the technical solutions disclosed in each embodiment of the present disclosure, relevant users should be informed in an appropriate manner about the type, scope of use, usage scenarios, etc. of the information related to the present disclosure in accordance with relevant laws and regulations, and obtain the permission of the relevant users. Here, it should be understood that the relevant users may include any type of right holder, such as individuals, enterprises, and organizations.
[0019] For example, when responding to a user's voluntary request, by clearly prompting the relevant user that the operation of requesting its execution by sending prompt information to the relevant user requires obtaining and using the relevant user's information, the relevant user can autonomously choose whether to provide information to software or hardware such as an electronic device, application program, server, or storage medium that executes the operation of the technical solution of the present disclosure according to the prompt information.
[0020] As a selective but non-limiting embodiment, the method of sending prompt information to the relevant user in response to receiving the user's voluntary request may be, for example, in the form of a pop-up window, and the prompt information may be presented in text in the pop-up window. In addition, the pop-up window may be provided with a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.
[0021] The above notice and user permission process are general in nature and do not constitute a limitation on how this disclosure can be implemented. It should be understood that other methods that comply with applicable laws and regulations may also be used to implement this disclosure.
[0022] As used herein, the term “model” is one that can learn the relationships between relevant inputs and outputs from training data, thereby enabling it to generate corresponding outputs for given inputs after training is complete. Model generation can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs using multiple processing units and provides corresponding outputs. A neural network model is an example of a model based on deep learning. In this specification, “model” may also be called a “machine learning model,” “learning model,” “machine learning network,” or “learning network,” and these terms are interchangeable within this specification.
[0023] Figure 1 shows a schematic diagram of an exemplary environment 100 that can realize the embodiments of this disclosure. Environment 100 relates to an application creation platform 110 and an application operation platform 140.
[0024] As shown in Figure 1, the application creation platform 110 can provide the user 105 with an environment for creating and distributing applications. The user 105 may also be called the application creation user or creator. In some embodiments, the application creation platform 110 may be a low-code platform that provides a collection of application creation tools. The application creation platform 110 can support the visualization development of various applications, thereby allowing developers to skip manual coding processes and accelerate the application development cycle and cost. The application creation platform 110 can support the user in developing any suitable platform for one or more types of applications, which may include, for example, an application platform, i.e., a platform based on a Platform as a Service (aPaaS). Such a platform can support the user in efficiently developing applications and performing operations such as application creation and application function tuning.
[0025] The application creation platform 110 may be deployed locally on the user 105's terminal device and / or supported by a service-side device. For example, a client of the application creation platform 110 may be running on the user 105's terminal device, and this client can support interaction between the user and the application creation platform 110 provided by the service-side. When the application creation platform 110 is running locally on the user's terminal device, the user 105 can directly interact with the local application creation platform 110 using the terminal device. When the application creation platform 110 is running on a service-side device, the service-side device can provide services to the client running on the terminal device based on a communication connection with the terminal device. The application creation platform 110 may present the user 105 with the relevant page 130 based on the user 105's actions so as to output information related to application creation to the user 105 and / or receive it from the user 105.
[0026] In some embodiments, the application creation platform 110 may be associated with a database that stores data or information necessary for the application creation process supported by the application creation platform 110. For example, the database may store corresponding code and descriptive information for composing each functional module of the application. The application creation platform 110 may perform operations such as calling, adding, deleting, and updating functional modules in the database. The database may store executable operations for different functional blocks. Exemplaryly, in a scenario where an application needs to be created, the application creation platform 110 may construct the application by calling the appropriate functional blocks from the database.
[0027] In embodiments of this disclosure, user 105 may create a target application 120 as needed on an application creation platform 110 and distribute the target application 120. The target application 120 may be distributed to any one suitable application operation platform 140, as long as the application operation platform 140 supports the operation of the target application 120. After distribution, the target application 120 may be used for operation by one or more users 145. Users 145 may be referred to as terminal users of the target application 120. In some embodiments, the target application 120 may include or be implemented as a digital assistant 122.
[0028] The digital assistant 122 may be configured to have intelligent conversation. In the example shown in Figure 1, the digital assistant 122 may be integrated into the target application 120 as part of the target application 120 and assist in performing task processing within the target application 120. In other examples, the digital assistant 122 may be configured as an independently operating application, such as a web page application or other type of application. In such examples, the digital assistant 122 and the target application 120 may be considered the same application. The digital assistant 122 is provided to assist the user with various task processing needs in different applications and scenarios. In the interaction process with the digital assistant 122, the user inputs an interaction message, and the digital assistant 122 provides a reply message in response to the user input. Generally, the digital assistant 122 can support the user inputting a question in natural language, and perform tasks and provide replies based on its understanding of natural language input and logical reasoning ability.
[0029] In some embodiments, the digital assistant 122 may interact with user 145 as a contact of user 145. For example, the digital assistant 122 may be implemented in an instant messaging (IM) application. The digital assistant 122 may interact with user 145 in a private session with user 145. In some embodiments, the digital assistant 122 may interact with multiple users in a group chat session that includes multiple users.
[0030] For each user 145, the client of the application operating platform 140 may present an interaction window 142 of the target application 120 or digital assistant 122, for example, a session window with the digital assistant 122, in the client interface. The user 145 may enter a session message in the session window, and the target application 120 may determine a reply message from the digital assistant 122 based on the created configuration information and present it to the user in the interaction window 142. In some embodiments, depending on the configuration of the target application 120, the interaction message with the target application 120 may include multimodal messages, such as text messages (e.g., natural language text), voice messages, image messages, video messages, etc.
[0031] Similar to the application creation platform 110, the application operation platform 140 may be deployed locally on each user's terminal device and / or supported by a service-side device. For example, a client of the application operation platform 140 may be running on the user's terminal device, and this client can support interaction between the user and the application operation platform 140 provided by the service-side. When the application operation platform 140 is run locally on the user's terminal device, the user 145 can directly interact with the local application operation platform 140 using the terminal device. When the application operation platform 140 is run on a service-side device, the service-side device can provide services to the client running on the terminal device based on a communication connection with the terminal device. The application operation platform 140 can present the user 145 with the relevant application page based on the user's actions, so as to output information related to application usage to the user 145 and / or receive it from the user 145.
[0032] In some embodiments, the implementation of at least some functions of the target application 120, and / or the implementation of at least some functions of the digital assistant 122 in the target application 120, may be based on a model. One or more models 150 may be invoked in the process of creating or running the target application 120. In the target application 120, the digital assistant 122 may use a model 155 to understand user input and provide a response to the user based on the output of the model 155.
[0033] During the creation process, the application creation platform 110 must use Model 155 to determine whether the operational results of the target application 120 meet expectations when testing the target application 120. During the operational process, in response to different operational requests from the user of the target application 120, the application operation platform 140 may need to use Model 155 to determine the response results to the user.
[0034] Although shown independently of the application creation platform 110 and the application operation platform 140, one or more models 155 may run on the application creation platform 110 and / or the application operation platform 140, or on other remote servers. In some embodiments, model 155 may be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model may be based on a language model (LM). A language model can acquire question-answering capabilities by learning from a large corpus. Model 155 may also be based on other suitable models.
[0035] The application creation platform 110 and / or the application operation platform 140 may be operated on appropriate electronic equipment. Electronic equipment here may be any type of equipment with computing capabilities, including terminal equipment or service-side equipment. Terminal equipment may 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, personal communication system (PCS) equipment, personal navigation equipment, personal digital assistants (PDAs), audio / video players, digital cameras / cameras, positioning equipment, television receivers, radio broadcast receivers, e-book equipment, game equipment, or any combination of the foregoing, including components and peripherals of these devices or any combination thereof. Service-side equipment may include, for example, computing systems / servers, such as mainframes, edge computing nodes, or computing equipment in a cloud environment. In some embodiments, the application creation platform 110 and / or the application operation platform 140 may be implemented based on cloud services.
[0036] The structure and functionality of Environment 100 are described for illustrative purposes only, and it should be understood that this does not imply any limitation on the scope of this disclosure. For example, Figure 1 shows a single user interacting with the application creation platform 110 and a single user interacting with the application operation platform 140, but in practice, multiple users may access the application creation platform 110 and each create a digital assistant, and each digital assistant may be used to interact with multiple users.
[0037] Currently, with the rapid development of digital assistants, user demand for them is gradually increasing. For example, in group chat scenarios, multiple users need to receive replies from a digital assistant. In group chat scenarios, traditional solutions only allow the digital assistant to reply to a specified question or to all question contexts of a specified user; it cannot reply based on the question contexts of multiple users, nor can it develop a conversational discussion between multiple people and the digital assistant on a given topic.
[0038] Embodiments of this disclosure propose an improved method for session interaction. In this method, a first session message is received from the first user to the digital assistant in a first topic of a group chat session including at least one user and the digital assistant. Based on contextual information related to the first topic, a first reply message from the digital assistant to the first session message is generated. The first reply message from the digital assistant is presented in the first topic. This method allows for replies based on the context of questions from multiple users and enables the development of conversational discussions between multiple people and the digital assistant on a given topic.
[0039] The following describes in detail some exemplary embodiments of this disclosure with reference to the drawings. It should be understood that the pages shown in the drawings are merely examples, and various page designs may actually exist. Each graphic element on a page may have a different configuration and visual representation, one or more of these elements may be omitted or replaced, and one or more other elements may be present. The embodiments of this disclosure are not limited in this respect.
[0040] Figure 2 shows flowcharts for session interaction according to some embodiments of the present disclosure. Flowchart 200 enables session interaction between at least one user 145 and a digital assistant 122.
[0041] In the following example, the description will be from the perspective of the application operating platform, as needed for consideration. For example, the user 145 and the digital assistant 122 will have a session interaction based on the pages presented by the application operating platform 140.
[0042] In some embodiments, user 145 may represent each user, for example, the first user, the second user, the third user, and so on. This disclosure is not limited thereto.
[0043] In some embodiments, the application operating platform 140 receives a first session message from a first user 145 to the digital assistant 122 in the first topic of a group chat session that includes at least one user 145 and the digital assistant 122. For example, the application operating platform 140 receives a first session message from user 145 that reads, "Please help me generate a customer order trend report." The acquisition of the first session message is described below with reference to blocks 210, 214 and 212, and 216.
[0044] Subsequently, the application operating platform 140 generates a first reply message for the digital assistant to the first session message based on contextual information related to the first topic. For example, in block 218, the digital assistant 122 obtains all session content related to the first topic as context. In block 220, the digital assistant 122 generates a first reply message based on the user 145's first session message and contextual information related to the first topic.
[0045] Accordingly, the first response message of the digital assistant may be presented in the first topic.
[0046] In embodiments of this disclosure, a first session message is received from a first user to the digital assistant in a first topic of a group chat session including at least one user and the digital assistant. A first reply message for the digital assistant is generated in response to the first session message based on contextual information related to the first topic. The first reply message for the digital assistant is presented in the first topic. This method allows for replies based on the context of questions from multiple users and enables the development of conversational discussions between multiple people and the digital assistant on a given topic.
[0047] Figures 3A to 3F show schematic diagrams of exemplary interfaces according to some embodiments of the present disclosure. It should be understood that the application interfaces shown in the drawings are merely examples, and various interface designs may actually exist. Each graphics element in the interface may have different configurations and different visual representations, one or more of these elements may be omitted or replaced, and one or more other elements may be present. The embodiments of the present disclosure are not limited in this respect.
[0048] In some embodiments, the first topic may be created in response to a session message from a user. For example, in a group chat session, the application operating platform 140 receives a second session message from a second user 145 to the digital assistant 122. For example, in block 210, user 145 asks a question to the digital assistant 122 within a general group chat session. Refer to the interface schematic diagram 301 shown in Figure 3A.
[0049] In the example shown in Figure 3A, the application operating platform 140 provides the user 145 with a session interaction page 330 in the interface schematic diagram 301. The session interaction page 330 includes a message list 320 and a group chat session page 310. The group chat session page 310 includes a function card 340 that is automatically generated by the digital assistant 122. For example, the function card automatically generated by the digital assistant 122 may include, but is not limited to, a corporate question answering function, a data update function, a data query function, and a BI report function, and this card can also be used to open signs, etc.
[0050] The group chat session page 310 also includes a second session message 343 from user 145 to the digital assistant 122. For example, the application operating platform 140 receives a session message from the second user to the digital assistant 122 in the group chat session and displays it on the group chat session page 310.
[0051] In some embodiments, the second session message includes a mention operation for the digital assistant 122. Exemplary, the mention operation may include @digital_assistant122. For example, a second user in a group chat session sends the message "@XX_assistant_please_help_generate_customer_order_trends_report," as shown in the second session message 343 in Figure 3A.
[0052] The application operating platform 140 creates a first topic. The creation of the first topic may be based on a question from the user to the digital assistant (i.e., issuing a second session message), or in response to the generation of a reply message to the second session message. For example, in block 214, the digital assistant 122 creates a topic within a general group chat session based on user 145 and replies. In some embodiments, within the group chat session, the application operating platform 140 receives a second session message from a second user 145 to the digital assistant 122. For example, in block 210, user 145 asks a question to the digital assistant 122 within a general group chat session. In block 212, user 145 asks a question to the digital assistant 122 within a topic group.
[0053] In some embodiments, the first topic includes at least a second session message and a second reply message from the digital assistant 122 to the second session message, as shown in schematic diagrams 302 and 303, for example, in Figures 3B and 3C.
[0054] In some embodiments, the digital assistant 122 determines a second reply message for a second session message. For example, in block 214, the digital assistant 122 creates a topic within a general group chat session based on user 145 and replies, as shown in topic 353 in schematic diagram 302 of Figure 3B. In block 216, the digital assistant 122 creates a topic within a topic group based on user 145 and replies.
[0055] The schematic diagram 303 shown in Figure 3C includes a session interaction page 330, which includes a message list 320 and a group chat session 310, which includes a topic area 355, which includes a second session message, as shown in message 354 in Figure 3C, and the second reply message, as shown in message 343 in Figure 3C.
[0056] When a user clicks on topic 353 shown in Figure 3B, topic area 355 is presented, as shown in Figure 3C. When a user 145 sends "XX Assistant, please help me generate a customer order trend report," XX Assistant replies to "XX Assistant, please help me generate a customer order trend report" with "We have already generated a customer order trend report, please review it," as shown in topic area 355 in Figure 3C.
[0057] In some embodiments, it is not necessary to create a topic for a general group chat. The digital assistant may reply directly to the user in the group chat session. If the user asks the digital assistant another question, the digital assistant may take at least some of the group messages previously sent by the user as context to generate a further reply. In some embodiments, whether or not to create a topic in a group chat session is configurable. For example, it may be configured by the creator when creating the application or digital assistant. In such cases, the same configuration is applied to different group chat sessions. Alternatively, for example, it may be configured by a group member with pre-configured permissions (e.g., group chat administration permissions). In such cases, different configurations may be applied to different group chat sessions.
[0058] The schematic diagrams 304 and 305 shown in Figures 3D and 3E include a session interaction page 330, which includes a message list 320 and a topic group session 360, and the topic group session 360 includes a topic 313. The topic 313 includes the user's session message, an input control 314 and a reply message 315 to the session message.
[0059] In some embodiments, the input control 314 may be used as a reply to a second session message.
[0060] For example, in a topic group, user A 145 may, in topic 313, refer to the digital assistant 122 and ask, "What's the weather like today?", and then click the input control 314 in Figure 3D to enter a message into topic 313.
[0061] In some embodiments, a second reply message formed when the digital assistant 122 replies to a second session message such as "@XX Assistant, what's the weather like today?" is shown in Figure 3E as 315 "@XX Assistant [card message]".
[0062] In some embodiments, clicking anywhere in topic 313 can display a topic window, which corresponds to topic 313, as shown in Figure 3F.
[0063] The schematic diagram 306 shown in Figure 3F includes a session interaction page 330, which includes a message list 320 and a topic window 333, and the topic window 333 includes a topic group session 360.
[0064] In some embodiments, topic window 333 is a topic window corresponding to a single topic 313 in topic group session 360, as shown in 360 in Figure 3F.
[0065] For example, in a topic group, if user A145 mentions "XX Assistant, what's the weather like today?", XX Assistant will respond to "XX Assistant, what's the weather like today?" with "Today's weather is as follows: XXX", as shown in Figure 3F.
[0066] In some examples, the second session message is not associated with an existing topic in the group chat session.
[0067] In some embodiments, a group chat session may include multiple users 145 and a digital assistant 122. In some embodiments, a group chat session may include a topic group consisting of at least one user 145 and a digital assistant 122. The topic group supports the two sessions in discussing multiple topics.
[0068] In some embodiments, the first topic is already created before the first session message is received. It may be understood that the first topic is automatically created by the digital assistant 122 before the first session message. In some embodiments, the first topic is created in response to a user trigger action in a group chat session. The first topic may be understood as being manually created by the user.
[0069] In some embodiments, in response to detecting a request to view a first topic in a group chat session, a topic area corresponding to the first topic is presented, and messages related to the first topic are presented within the topic area. For example, in a typical group chat, the topic area is as shown in topic area 355 in Figure 3C. In a topic group, the topic area may be understood as topic window 333 in Figure 3F.
[0070] In embodiments of this disclosure, a first session message is received from a first user to the digital assistant in a first topic of a group chat session including at least one user and the digital assistant. A first reply message for the digital assistant is generated in response to the first session message based on contextual information related to the first topic. The first reply message for the digital assistant is presented in the first topic. This method allows for replies based on the context of questions from multiple users and enables the development of conversational discussions between multiple people and the digital assistant on a given topic.
[0071] Figure 4 shows a flowchart of process 400 for session interaction according to some embodiments of the present disclosure. Process 400 may be implemented on the application operating platform 140. Process 400 will be described below with reference to Figure 1.
[0072] In block 410, the application operating platform 140 receives a first session message from the first user to the digital assistant in a first topic of a group chat session that includes at least one user and the digital assistant.
[0073] In block 420, the application operation platform 140 generates a first response message from the digital assistant to the first session message based on contextual information related to the first topic.
[0074] In block 430, the application operating platform 140 presents the first response message from the digital assistant on the first topic.
[0075] In some embodiments, process 400 further includes receiving a second session message from a second user to the digital assistant in a group chat session, and creating a first topic that includes at least the second session message and the digital assistant's second reply message to the second session message.
[0076] In some embodiments, the second session message includes a reference operation to the digital assistant.
[0077] In some examples, the second session message is not associated with an existing topic in the group chat session.
[0078] In some embodiments, a group chat session includes multiple users and a digital assistant.
[0079] In some embodiments, the first topic is one that has already been created before receiving the first session message.
[0080] In some embodiments, the first topic is created in response to a user trigger action in a group chat session.
[0081] In some embodiments, process 400 further includes, in response to detecting a viewing request for a first topic in a group chat session, presenting a topic area corresponding to the first topic and presenting messages related to the first topic within the topic area.
[0082] Figure 5 shows a schematic structural block diagram of a device 500 for session interaction according to some embodiments of the present disclosure. The device 500 may be implemented in, for example, an application operating platform 110, or may be included therein. Each module / component in the device 500 may be implemented by hardware, software, firmware, or any combination thereof.
[0083] As shown in the figure, the device 500 includes a receiving module 510 configured to receive a first session message from a first user to a digital assistant in a first topic of a group chat session that includes at least one user and a digital assistant.
[0084] The device 500 further comprises a generation module 520 configured to generate a first response message for a digital assistant to a first session message based on contextual information related to a first topic.
[0085] The device 500 further comprises a presentation module 530 configured to present a first reply message of the digital assistant on a first topic.
[0086] In some embodiments, in a group chat session, the receiving module 510 is further configured to receive a second session message from a second user to the digital assistant and to create a first topic that includes at least the second session message and the digital assistant's second reply message to the second session message.
[0087] In some embodiments, the second session message includes a reference operation to the digital assistant.
[0088] In some examples, the second session message is not associated with an existing topic in the group chat session.
[0089] In some embodiments, a group chat session includes multiple users and a digital assistant.
[0090] In some embodiments, the first topic is one that has already been created before receiving the first session message.
[0091] In some embodiments, the first topic is created in response to a user trigger action in a group chat session.
[0092] In some embodiments, the presentation module 530 is further configured to present a topic area corresponding to the first topic in response to detecting a viewing request for the first topic in a group chat session, and to present messages related to the first topic in the topic area.
[0093] In some embodiments, the application operation platform 140 receives a first session message from a first user 145 to the digital assistant 122 in a session involving at least one user 145 and the digital assistant 122. For example, the application operation platform 140 receives a first session message from user 145 that reads, "Please help me generate a customer order trend report."
[0094] In some embodiments, the first session message may include a reference operation to the digital assistant. In some embodiments, the first session message may be sent directed to the digital assistant in any other manner.
[0095] The session described herein may be any appropriate type of session, such as a group chat session. In some embodiments, the session may be a general group chat session, for example, as described in blocks 210 and 214 shown in Figure 2. In some embodiments, the session may be a topic group chat session, for example, in blocks 212 and 216 shown in Figure 2. In a topic group chat session, each session message may belong to a single topic. In contrast, in a general group chat session, unless otherwise specified, session messages do not belong to a topic. The application operating platform 140 may then determine contextual information associated with the first session message, depending on the trigger mode of the first session message.
[0096] In some embodiments, context information may be determined based on time-dimensional information associated with the first session message. For example, context information may be determined based on session messages within this session whose transmission time is less than a threshold from the transmission time of the first session message.
[0097] Alternatively or additionally, in some embodiments, contextual information may be determined based on user-dimensional information associated with the first session message. For example, if the first session message refers to or is directed towards one or more users, contextual information may be determined based on information about the one or more users referred to or directed towards (e.g., the message being sent).
[0098] In some embodiments, the trigger mode may be conversational, including a conversation in a typical group chat session. In other words, in such a conversational trigger mode, the first user does not have to send a first session message to any topic. In such embodiments, the application operating platform 140 may determine contextual information based on at least the first session message. For example, if user 145 sends a first session message stating "Please help me generate a customer order trend report," the application operating platform 140 or the digital assistant may determine contextual information based on the content of this session message.
[0099] In some embodiments, the trigger mode may include triggering in a topic-based manner, i.e., session messages are sent to a certain topic. For example, such a topic may be a topic in a general group chat session. Alternatively, such a topic may be a topic in a topic group chat session. In such embodiments, contextual information may be determined based on one or more session messages in this topic.
[0100] Furthermore, based on the determined context information, the digital assistant may generate a first reply message to the first session message. For example, in block 218, the digital assistant 122 obtains all session content related to the first topic as context. In block 220, the digital assistant 122 generates a first reply message based on the user 145's first session message and the context information related to the first topic.
[0101] In some embodiments, a machine learning model may be used to generate the first reply message. For example, a prompt word may be generated based on contextual information, and the generated prompt word may be sent to the machine learning model. At least a portion of the first reply message may then be obtained from the machine learning model.
[0102] After receiving the first reply message, the digital assistant may present the first reply message according to the presentation mode associated with the trigger mechanism. The presentation mode may be used to indicate the location where the reply message is presented, the style of presentation, and so on.
[0103] In some embodiments, as described above, the first session message may be triggered in conversational form, i.e., the trigger mode is to be triggered in conversational form. In such embodiments, since the first session message does not address any topic, a first topic may be created in the session, and the first reply message may be presented in the first topic.
[0104] In some embodiments, as described above, the first session message may be triggered for a topic (also called a second topic). Then, the first reply message may be presented directly in the second topic.
[0105] In the embodiments of this disclosure, responses can be provided based on the context of questions from multiple users, and conversational discussions between multiple people and the digital assistant on a given topic can also be developed. This is advantageous in further improving the efficiency of collaboration between the digital assistant and the user, particularly in multiple user scenarios.
[0106] The following describes some exemplary embodiments of this disclosure with reference to the exemplary interfaces shown in Figures 3A to 3F. Figures 3A to 3F show schematic diagrams of exemplary interfaces according to some embodiments of this disclosure. It should be understood that the application interfaces shown in the drawings are merely examples, and various interface designs may actually exist. Each graphics element in the interface may have different configurations and different visual representations, one or more of these elements may be omitted or replaced, and one or more other elements may be present. The embodiments of this disclosure are not limited in this respect.
[0107] In some embodiments, the first topic may be created in response to a session message from the user. Specifically, the application operating platform 140 may receive a session message from the user to the digital assistant 122 in a group chat session. Such a group chat session may be a general group chat session. For example, in block 210, the user asks a question to the digital assistant 122 in a general group chat session.
[0108] Refer to the interface schematic diagram 301 shown in Figure 3A. In the example in Figure 3A, the application operating platform 140 provides the user 145 with a session interaction page 330. The session interaction page 330 includes a message list 320 and a group chat session page 310. On the group chat session page 310, a function card 340, also called a message card, is provided, which is automatically generated by the digital assistant 122. For example, the function card automatically generated by the digital assistant 122 may include, but is not limited to, entries for functions possessed by the digital assistant 122, the knowledge question answering function shown in Figure 3A, the data update function, the data query function, and the business intelligence (BI) reporting function. This card can also be used to open signs, etc.
[0109] The group chat session page 310 also displays session messages 343 from user 145 to digital assistant 122. For example, the application operating platform 140 receives session messages from the user to digital assistant 122 in a group chat session and displays them on the group chat session page 310.
[0110] In some embodiments, session messages may include a reference operation to the digital assistant 122. Exemplary, the reference operation may include @digital_assistant122. For example, a user in a group chat session sends the message "@XX_assistant_please_help_generate_customer_order_trends_report," as shown in session message 343 in Figure 3A.
[0111] In some embodiments, session messages do not need to be associated with existing topics in a group chat session. For example, in a typical group chat session, the user has not entered any messages for any topic, such as session message 343 shown in Figure 3A.
[0112] Furthermore, the application operating platform 140 creates a first topic. The creation of the first topic may be based on a question from the user to the digital assistant (i.e., issuing a session message), or it may be in response to the generation of a reply message to the session message. For example, in block 212, the user asks a question to the digital assistant in a general group chat session. In block 214, the digital assistant 122 creates a topic in the general group chat session based on the user's message and replies to the user.
[0113] The first topic created includes at least session messages sent by the user to the digital assistant and the digital assistant 122's reply messages to the session messages, for example, schematic diagrams 302 and 303 shown in Figures 3B and 3C. The digital assistant 122 determines the reply message for the session message. For example, topic 353 shown in Figure 3B includes session message 343 shown in Figure 3A and reply message 351 for session message 343.
[0114] In some embodiments, when a viewing request for a first topic is detected in a group chat session, the application operating platform 140 may present a topic area corresponding to the first topic and present messages related to the first topic in the topic area. The schematic diagram 303 shown in Figure 3C includes a session interaction page 330, which includes a message list 320 and a group chat session 310, and the group chat session 310 includes a topic area 355. The topic area 355 includes a session message 354 and a reply message 363 to the session message 354.
[0115] For example, when a user clicks on the card corresponding to topic 353 shown in Figure 3B, topic area 355 may be presented, as shown in Figure 3C. When a user 145 sends "XX Assistant, please help me generate a customer order trend report," XX Assistant replies to "XX Assistant, please help me generate a customer order trend report" with "We have already generated a customer order trend report, please review it," as shown in topic area 355 in Figure 3C.
[0116] In some embodiments, it is not necessary to create a topic for a general group chat. The digital assistant may reply directly to the user in the group chat session. If the user asks the digital assistant another question, the digital assistant may take at least some of the group messages previously sent by the user as context to generate a further reply. In some embodiments, whether or not to create a topic in a group chat session is configurable. For example, it may be configured by the creator when creating the application or digital assistant. In such cases, the same configuration is applied to different group chat sessions. Alternatively, for example, it may be configured by a group member with pre-configured permissions (e.g., group chat administration permissions). In such cases, different configurations may be applied to different group chat sessions.
[0117] In some embodiments, a topic may have already been created before the first session message is received. For example, a typical group chat session may have topics previously created by the user. If the user refers to the digital assistant in such a topic, the digital assistant may respond to the user based on the context of that topic.
[0118] For example, in a topic group chat session, each message is directed at a single topic. A user may mention a digital assistant in one of those topics or wake up the digital assistant in any other appropriate manner.
[0119] The schematic diagrams 304 and 305 shown in Figures 3D and 3E, respectively, include a session interaction page 330, which includes a message list 320 and a topic group chat session 360. The topic group chat session 360 includes a topic 313 that has already been created. The topic 313 includes a user's session message, an input control 314, and a reply message 315 to the session message. In some embodiments, the input control 314 may be used as a reply to the session message from the user.
[0120] In this example, in a topic group chat session, User A refers to the digital assistant 122 in topic 313 and asks, "What's the weather like today?" User A or another user may click the input control 314 in Figure 3D to type a message in topic 313.
[0121] The reply message formed when the digital assistant 122 responds to a session message such as "@XX Assistant, what's the weather like today?" is shown in the message 315 "@XX Assistant [card message]" in Figure 3E.
[0122] In some embodiments, when a user clicks anywhere in the interface area corresponding to topic 313, messages in topic 313 may be displayed. See the example described in Figure 3F. The schematic diagram 306 shown in Figure 3F includes a session interaction page 330, which includes a message list 320 and a topic window 333. The topic window 333 may be a topic window corresponding to a single topic 313 in a topic group chat session 360.
[0123] For example, in a topic group chat session, if user A asks the digital assistant "XX Assistant, what's the weather like today?", XX Assistant will reply to "XX Assistant, what's the weather like today?" with "Today's weather is as follows: XXX", as shown in Figure 3F.
[0124] In some embodiments, a group chat session may include multiple users 145 and a digital assistant 122. In some embodiments, a group chat session may include a topic group chat session consisting of at least one user 145 and a digital assistant 122. A topic group chat session supports two or more sessions discussing multiple topics.
[0125] In some embodiments, the topic is already created before the first session message is received. For example, as mentioned above, a group chat session is a topic group chat session. Also, for example, in a general group chat session, a topic is created and a user refers to a digital assistant in this topic. In some embodiments, the topic is created in response to a user trigger action in the group chat session. For example, the topic may be manually created by a user.
[0126] In some embodiments, in response to detecting a request to view a first topic in a group chat session, a topic area corresponding to the first topic is presented, and messages related to the first topic are presented within the topic area. For example, in a typical group chat session, the topic area is as shown in topic area 355 in Figure 3C. In a topic group chat session, the topic area may be understood as topic window 333 in Figure 3F.
[0127] This approach allows for responses based on the context of questions from multiple users, and enables the development of conversational discussions between multiple people and the digital assistant on a given topic.
[0128] Figure 6 shows a flowchart of process 600 for session interaction according to some embodiments of the present disclosure. Process 600 may be implemented on the application operating platform 140. Process 600 will be described below with reference to Figure 1.
[0129] In block 610, the application operating platform 140 receives a first session message from a first user to a digital assistant in a session that includes at least one user and a digital assistant.
[0130] In block 620, the application operation platform 140 determines the context information associated with the first session message, depending on the trigger mode of the first session message.
[0131] In block 630, the application operation platform 140 generates a first response message from the digital assistant to the first session message based on contextual information.
[0132] In block 640, the application operation platform 140 presents a first reply message depending on the presentation mode associated with the trigger scheme.
[0133] In some embodiments, the trigger mode includes triggering in a conversational manner, and the terminal device 110 determines contextual information based on at least a first session message.
[0134] In some embodiments, the application operating platform 140 creates a first topic in a session that includes at least a first session message, and the application operating platform 140 presents a first reply message in the first topic.
[0135] In some embodiments, the trigger mode includes a trigger for a second topic in the session, and the application operating platform 140 determines contextual information based on one or more session messages in the second topic.
[0136] In some embodiments, the application operation platform 140 presents a first reply message in a first topic.
[0137] In some embodiments, a session includes a topic group chat session.
[0138] In some embodiments, the first session message includes a reference operation to the digital assistant.
[0139] In some embodiments, a session includes multiple users and a digital assistant.
[0140] In some embodiments, upon detecting a request to access a first topic in a session, the terminal device 110 presents a topic area corresponding to the first topic and presents messages related to the first topic within that topic area.
[0141] In some embodiments, the application operation platform 140 provides a machine learning model with prompt words generated based on contextual information and retrieves at least a portion of a first reply message from the machine learning model.
[0142] In some embodiments, the application operation platform 140 determines contextual information based on at least one of time-dimension information associated with the first session message and user-dimension information associated with the first session message.
[0143] Figure 7 shows a schematic structural block diagram of a device 700 for session interaction according to some embodiments of the present disclosure. The device 700 may be implemented in, for example, an application operating platform 110, or may be included therein. Each module / component in the device 700 may be implemented by hardware, software, firmware, or any combination thereof.
[0144] As shown in the figure, the device 700 includes a receiving module 710 configured to receive a first session message from a first user to a digital assistant in a session involving at least one user and a digital assistant; a context information determination module 720 configured to determine context information associated with the first session message depending on the trigger mode of the first session message; a first reply message generation module 730 configured to generate a first reply message for the digital assistant to the first session message based on the context information; and a presentation module 740 configured to present the first reply message depending on the presentation mode associated with the trigger scheme.
[0145] In some implementations, the trigger mode includes triggering in a conversational manner, and the context information determination module 720 is further configured to determine context information based on at least a first session message.
[0146] In some implementations, the presentation module 740 is further configured to create a first topic in a session that includes at least a first session message, and to present a first reply message in the first topic.
[0147] In some implementations, the trigger mode includes a trigger for a second topic in the session, and the context information determination module 720 is further configured to determine context information based on one or more session messages in the second topic.
[0148] In some implementations, the presentation module 740 is further configured to present a first reply message on a first topic.
[0149] In some implementations, sessions include topic group chat sessions.
[0150] In some implementations, the first session message includes a reference to digital assistants.
[0151] In some implementations, a session includes multiple users and a digital assistant.
[0152] In some implementations, the device 700 further includes a browsing request processing module configured to, in response to detecting a browsing request for a first topic in a session, present a topic area corresponding to the first topic and present messages related to the first topic in the topic area.
[0153] In some implementations, the first reply message generation module 730 is further configured to provide a prompt word generated based on contextual information to a machine learning model and to retrieve at least a portion of the first reply message from the machine learning model.
[0154] In some implementations, the context information determination module 720 is further configured to determine context information based on at least one of the time-dimensional information associated with the first session message and the user-dimensional information associated with the first session message.
[0155] Figure 8 shows a block diagram of an electronic device 800 that can implement one or more embodiments of the present disclosure. It should be understood that the electronic device 800 shown in Figure 8 is illustrative and does not imply any limitation on the function and scope of the embodiments described herein. The electronic device 800 shown in Figure 8 may include, or be implemented as, the application operating platform 140 of Figure 1 or the device 500 of Figure 5.
[0156] As shown in Figure 8, the electronic device 800 is a general-purpose electronic device. The components of the electronic device 800 may include, but are not limited to, one or more processors or processing units 810, memory 820, storage devices 830, one or more communication units 840, one or more input devices 850, and one or more output devices 870. The processing unit 810 may be an actual or virtual processor and can perform various processes based on a program stored in memory 820. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of the electronic device 800.
[0157] The electronic device 800 generally includes multiple computer storage media. Such media may be any obtainable media accessible to the electronic device 800, and may include, but are not limited to, volatile and non-volatile media, and removable and non-removable media. Memory 820 may be volatile memory (e.g., registers, caches, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or any combination thereof. Storage device 830 may be removable or non-removable media, and may include machine-readable media, such as flash memory drives, magnetic disks, or any other media, which can be used to store information and / or data and are accessible within the electronic device 800.
[0158] The electronic device 800 may further include other removable / non-removable, volatile / non-volatile storage media. Not shown in Figure 8, a magnetic disk drive for reading from or writing to removable, non-volatile magnetic disks (e.g., “floppy disks”) and an optical disk drive 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) by one or more data medium interfaces. The memory 820 may also include a computer program product 825, which includes one or more program modules, these program modules configured to perform various methods or operations of various embodiments of the present disclosure.
[0159] The communication unit 840 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 800 can be implemented by a single computing cluster or multiple computing machines, which can communicate via a communication connection. Therefore, the electronic device 800 can operate in a network environment using logical connections with one or more other servers, network personal computers (PCs), or other network nodes.
[0160] The input device 850 may be one or more input devices, such as a mouse, keyboard, or trackball. The output device 870 may be one or more output devices, such as a display, speaker, or printer. The electronic device 800 may further communicate with one or more external devices (not shown), such as a storage device or display device, via the communication unit 840 as needed, with one or more devices for user interaction with the electronic device 800, or with any devices (e.g., a network card or modem) for communication between the electronic device 800 and one or more other electronic devices. Such communication may be performed via an input / output (I / O) interface (not shown).
[0161] An exemplary embodiment of the present disclosure provides a computer-readable storage medium in which computer-executable instructions are stored, wherein the computer-executable instructions implement a method that is executed by a processor and described above. An exemplary embodiment of the present disclosure further provides a computer program product which includes computer-executable instructions that are tangibly stored in a non-temporary computer-readable medium, wherein the computer-executable instructions implement a method that is executed by a processor and described above.
[0162] Herein, each aspect of the disclosure is described with reference to flowcharts and / or block diagrams of methods, apparatus, devices, and computer program products implemented pursuant to the disclosure. It should be understood that each block in the flowcharts and / or block diagrams, and each combination of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.
[0163] By providing these computer-readable program instructions to the processing units of a general-purpose computer, a dedicated computer, or other programmable data processing device, a machine can be generated, thereby generating a device that, when these instructions are executed by the processing units of the computer or other programmable data processing device, implements the functions / operations defined in one or more blocks in a flowchart and / or block diagram. These computer-readable program instructions may be stored in a computer-readable storage medium, and by using these instructions to operate a computer, programmable data processing device, and / or other device in a specific manner, the computer-readable medium storing the instructions will contain a product containing instructions that implement various modes of the functions / operations defined in one or more blocks in a flowchart and / or block diagram.
[0164] Computer-readable program instructions may be loaded into a computer, other programmable data processing device, or other device, thereby generating a process implemented by the computer by executing a series of operational steps on the computer, other programmable data processing device, or other device, and thereby the instructions executed on the computer, other programmable data processing device, or other device implement the functions / operations defined in one or more blocks in a flowchart and / or block diagram.
[0165] The flowcharts and block diagrams in the drawings illustrate the implementable system architectures, functions, and operations of systems, methods, and computer program products in multiple implementations of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of an instruction, and a module, program segment, or part of an instruction may contain one or more executable instructions for implementing a defined logical function. In some implementations as replacements, the functions described in a block may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed essentially in parallel, or in reverse order depending on the function. Note that each block in a block diagram and / or flowchart, and combinations of blocks in a block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the defined function or operation, or by a combination of dedicated hardware and computer instructions.
[0166] The above descriptions of the various realizations of this disclosure are illustrative, not exhaustive, and not limited to the realizations disclosed. Many modifications and changes will be apparent to those skilled in the art without departing from the scope and spirit of the realizations described. The choice of terms used herein is intended to best interpret the principles of each realization, actual applications, or improvements in the technology in the market, or to enable those other skilled in the art to understand each realization disclosed herein.
Claims
1. In a session involving at least one user and a digital assistant, receiving a first session message from the first user to the digital assistant, Depending on the trigger mode of the first session message, the context information associated with the first session message is determined, Based on the context information, a first reply message of the digital assistant to the first session message is generated, A session interaction method comprising presenting the first reply message in accordance with the presentation mode associated with the trigger method.
2. The trigger mode includes triggering in a conversational manner, and determining the context information is The method according to claim 1, comprising determining the context information based on at least the first session message.
3. Presenting the aforementioned first reply message means In the aforementioned session, create a first topic that includes at least the first session message, The method of claim 2, comprising presenting the first reply message in the first topic.
4. The trigger mode includes a trigger for a second topic in the session, and determining the context information is: The method according to claim 1, comprising determining the context information based on one or more session messages in the second topic.
5. Presenting the aforementioned first reply message means The method according to claim 4, comprising presenting the first reply message in the first topic.
6. The method according to claim 4, wherein the session includes a topic group chat session.
7. The method according to claim 1, wherein the first session message includes a reference operation to the digital assistant.
8. The method according to claim 1, wherein the session includes a plurality of users and the digital assistant.
9. The method according to claim 1, further comprising, in response to detecting a request to view a first topic in the session, presenting a topic area corresponding to the first topic, and presenting messages related to the first topic in the topic area.
10. Generating the first reply message of the digital assistant to the first session message is: The prompt words generated based on the aforementioned context information are provided to the machine learning model, The method according to claim 1, comprising obtaining at least a portion of the first reply message from the machine learning model.
11. Determining the aforementioned context information means The method according to claim 1, comprising determining the context information based on at least one of time-dimension information associated with the first session message and user-dimension information associated with the first session message.
12. A receiving module configured to receive a first session message from a first user to a digital assistant in a session including at least one user and a digital assistant, A context information determination module configured to determine context information associated with the first session message in accordance with the trigger mode of the first session message, A first reply message generation module configured to generate a first reply message of the digital assistant to the first session message based on the context information, A device for session interaction comprising: a presentation module configured to present the first reply message in accordance with the presentation mode associated with a trigger scheme.
13. An electronic device comprising at least one processing unit and at least one memory, The at least one memory is coupled to the at least one processing unit and stores instructions to be executed by the at least one processing unit. An electronic device that, when the instruction is executed by the at least one processing unit, causes the electronic device to perform the method according to any one of claims 1 to 11.
14. A computer-readable storage medium storing a computer program that is executed by a processor to implement the method described in any one of claims 1 to 11.