Method, apparatus, device, and storage medium for conversation interaction

Abstract

Embodiments of the present disclosure provide methods, apparatuses, devices, and storage media for conversational interaction. The method includes: in a conversation between a user and a digital assistant, in response to receiving a first conversation message from the user, presenting a first reply message of the digital assistant to the first conversation message, the first reply message including a first content, the first content being generated by a model based on the user's needs corresponding to the first conversation message; in response to receiving a collection request for the first content, adding the first content in the first reply message to the user's content collection page; and in response to detecting a content viewing request, presenting a second content in the content collection page, the second content being regenerated by the model based on the user's needs. Thus, by providing a modular, simple-input conversational interaction solution, allowing users to conveniently and quickly view the content of the digital assistant's historical replies, the interaction efficiency between the user and the digital assistant can be improved.

Description

[0001] This application claims priority to the Chinese invention patent application entitled “Methods, Apparatus, Devices and Storage Medium for Conversational Interaction” filed on November 8, 2023, with application number 202311483250.0, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to methods, apparatuses, devices, and computer-readable storage media for conversational interaction. Background Art

[0003] With the development of information technology, various terminal devices can provide a variety of services for people in work and life. Applications that provide these services can be deployed on these devices. Terminal devices present content and interact with users through the application's user interface, meeting their various needs. Therefore, a rich application interface is an important means of enhancing the user experience. Terminal devices or applications can provide users with digital assistant-like functions to assist them in using the terminal device or application. Improving the flexibility of user interaction with digital assistants is a current technical challenge. Summary of the Invention

[0004] In a first aspect of the present disclosure, a method for conversational interaction is provided. The method comprises: in a conversation between a user and a digital assistant, in response to receiving a first conversation message from the user, presenting a first reply message from the digital assistant to the first conversation message, the first reply message including first content, the first content being generated by a model based on user requirements corresponding to the first conversation message; in response to receiving a collection request for the first content, adding the first content in the first reply message to a content collection page of the user; and in response to detecting a content viewing request, presenting second content on the content collection page, the second content being regenerated by the model based on user requirements.

[0005] In a second aspect of the present disclosure, a device for conversational interaction is provided. The device includes: a message presentation module configured to, in a conversation between a user and a digital assistant, present a first reply message of the digital assistant to the first conversation message in response to receiving a first conversation message from the user, wherein the first reply message includes first content, and the first content is generated by a model based on user requirements corresponding to the first conversation message; a content adding module configured to, in response to receiving a collection request for the first content, add the first content in the first reply message to the user's content collection page; and a content presentation module configured to, in response to detecting a content viewing request, present second content in the content collection page, wherein the second content is regenerated by the model based on user requirements.

[0006] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the electronic device to perform the method of the first aspect.

[0007] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the medium, and when the computer program is executed by a processor, the method of the first aspect is implemented.

[0008] It should be understood that the content described in this section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0010] Figure 1 A schematic diagram illustrating an example environment in which embodiments of the present disclosure can be implemented;

[0011] Figure 2 A flowchart illustrating the information flow of a conversation interaction according to some embodiments of the present disclosure;

[0012] Figure 3 An example of a client interface for session interaction according to some embodiments of the present disclosure is shown;

[0013] Figure 4 An example of a content collection page according to some embodiments of the present disclosure is shown;

[0014] Figure 5 A flowchart illustrating a process for conversation interaction according to some embodiments of the present disclosure is shown;

[0015] Figure 6 A schematic structural block diagram of an apparatus for conversation interaction according to some embodiments of the present disclosure is shown; and

[0016] Figure 7 A block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented is shown. DETAILED DESCRIPTION

[0017] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0018] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, i.e., "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below.

[0019] Herein, unless explicitly stated otherwise, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0020] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0021] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the type, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and authorization should be obtained from relevant users in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.

[0022] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to the software or hardware such as the electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.

[0023] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message may be sent to the relevant user in the form of a pop-up window, in which the prompt message may be presented in text form. Furthermore, the pop-up window may also include a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.

[0024] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure. The activation of the digital assistant-related functions of the embodiment of the present disclosure, the data obtained, the processing and storage of the data, etc., shall all obtain the prior authorization of the user and other rights holders associated with the user, and shall comply with the provisions of relevant laws and regulations and the rules of agreement between rights holders.

[0025] As used herein, the term "model" can learn the association between corresponding inputs and outputs from training data, so that after training is completed, corresponding outputs can be generated for given inputs. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article.

[0026] Figure 1 FIG. 1 is a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. The environment 100 includes an application creation platform 110 and an application execution platform 140 .

[0027] like Figure 1 As shown, the application creation platform 110 can provide an application creation and publishing environment for the user 105. The user 105 can be referred to as an application creation user or creator. In some embodiments, the application creation platform 110 can be a low-code platform that provides a collection of tools for application creation. The application creation platform 110 can support visual development of various types of applications, allowing developers to skip the manual coding process and speed up the application development cycle and cost. The application creation platform 110 can support any appropriate platform for users to develop one or more types of applications, for example, it can include a platform based on Application Platform as a Service (aPaaS). Such a platform can support users to efficiently develop applications and implement operations such as application creation and application function adjustment.

[0028] The application creation platform 110 can be deployed locally on the terminal device of the user 105, and / or can be supported by a server-side device. For example, the terminal device of the user 105 can run a client of the application creation platform 110, which can support the interaction between the user and the application creation platform 110 provided by the server. In the case where the application creation platform 110 runs locally on the user's terminal device, the user 105 can directly use the terminal device to interact with the local application creation platform 110. In the case where the application creation platform 110 runs on the server-side device, the server-side device can realize the service provision of the client running in the terminal device based on the communication connection between the terminal device and the server-side device. The application creation platform 110 can present a corresponding page 130 to the user 105 based on the operation of the user 105 to output and / or receive information related to application creation to the user 105 and / or from the user 105.

[0029] In some embodiments, the application creation platform 110 may be associated with a corresponding database that stores data or information required for the application creation process supported by the application creation platform 110. For example, the database may store code and description information corresponding to each functional module that constitutes the application. The application creation platform 110 may also perform operations such as calling, adding, deleting, and updating the functional modules in the database. The database may also store operations that can be performed on different functional modules. For example, in a scenario where an application is to be created, the application creation platform 110 may call the corresponding functional modules from the database to build the application.

[0030] In an embodiment of the present disclosure, a user 105 can create a target application 120 as needed on an application creation platform 110 and publish the target application 120. The target application 120 can be published to any appropriate application execution platform 140, as long as the application execution platform 140 can support the operation of the target application 120. After publication, the target application 120 can be used to be operated by one or more users 145. The users 145 can be referred to as end users of the target application 120. In some embodiments, the target application 120 may include or be implemented as a digital assistant 122.

[0031] The digital assistant 122 can be configured to have intelligent conversation capabilities. Figure 1In the example shown, the digital assistant 122 can be integrated into the target application 120 to assist in performing task processing within the target application 120 as part of the target application 120. In other examples, the digital assistant 122 can be configured as an independently running application, such as a web application or other type of application. In such an example, the digital assistant 122 and the target application 120 can be regarded as the same application. The digital assistant 122 is provided to assist users with various task processing needs in different applications and scenarios. During the interaction with the digital assistant 122, the user inputs an interactive message, and the digital assistant 122 provides a reply message in response to the user input. Generally, the digital assistant 122 can support users to input questions in natural language, and perform tasks and provide replies based on the understanding of natural language input and logical reasoning ability.

[0032] In some embodiments, digital assistant 122 can interact with user 145 as a contact. For example, digital assistant 122 can be implemented in an instant messaging (IM) application. Digital assistant 122 can interact with user 145 in a single chat session with user 145. In some embodiments, digital assistant 122 can interact with multiple users in a group chat session including multiple users.

[0033] For each user 145, the client of the application execution platform 140 can present an interaction window 142 of the target application 120 or the digital assistant 122 in the client interface, such as a conversation window with the digital assistant 122. The user 145 can enter a conversation message in the conversation window, and the target application 120 can determine a reply message of 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 can include messages in multimodal forms, such as text messages (e.g., natural language text), voice messages, image messages, video messages, etc.

[0034] Similar to the application creation platform 110, the application running platform 140 can be deployed locally on the terminal device of each user 145, and / or can be supported by a server-side device. For example, the terminal device of user 145 can run a client of the application running platform 140, which can support the interaction between the user and the application running platform 140 provided by the server. In the case where the application running platform 140 runs locally on the user's terminal device, the user 145 can directly use the terminal device to interact with the local application running platform 140. In the case where the application running platform 140 runs on the server-side device, the server-side device can, based on the communication connection with the terminal device, implement service provision for the client running in the terminal device. The application running platform 140 can present the corresponding application page to the user 145 based on the operation of the user 145, so as to output and / or receive information related to application use to the user 145 and / or receive information from the user 145.

[0035] In some embodiments, at least some of the functionality of the target application 120 and / or at least some of the functionality of the digital assistant 122 in the target application 120 can be implemented based on a model. During the creation or execution of the target application 120, one or more models 155 can be called. In the target application 120, the digital assistant 122 can use the model 155 to understand user input and provide a response to the user based on the output of the model 155.

[0036] During the creation process, the application creation platform 110 tests the target application 120 using the model 155 to ensure that the target application 120's operating results meet expectations. During operation, in response to various user operation requests of the target application 120, the application execution platform 140 may need to use the model 155 to determine the user's response results.

[0037] Although shown as being independent of the application creation platform 110 and the application execution platform 140, one or more models 155 can run on the application creation platform 110 and / or the application execution platform 140, or other remote servers. In some embodiments, the model 155 can be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model can be based on a language model (LM). A language model can have question-answering capabilities by learning from a large amount of corpus. The model 155 can also be based on other appropriate models.

[0038] The application creation platform 110 and / or the application execution platform 140 can run on appropriate electronic devices. The electronic devices here can be any type of device with computing capabilities, including terminal devices or server devices. The terminal device can be any type of mobile terminal, fixed terminal or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a gaming device or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device can, for example, include a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. In some embodiments, the application creation platform 110 and / or the application execution platform 140 can be implemented based on a cloud service.

[0039] It should be understood that the structure and functionality of the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure. Figure 1 A single user interacting with the application creation platform 110 and a single user interacting with the application execution platform 140 are shown, but in reality multiple users can access the application creation platform 110 to each create a digital assistant, and each digital assistant can be used to interact with multiple users.

[0040] Digital assistants can serve as effective tools for people's work, learning, and daily life. Typically, interactions with digital assistants are primarily conversational, characterized by fragmentation and uncertainty. However, in some scenarios (such as corporate offices), the data analysis and knowledge Q&A output provided by digital assistants have long-term reusable value. It is desirable to provide a way to access the content output by digital assistants, allowing users to reuse or view this content with simple operations.

[0041] According to an embodiment of the present disclosure, an improved solution for conversational interaction is provided. According to this solution, in a conversation between a user and a digital assistant, in response to receiving a first conversation message from the user, the digital assistant presents a first reply message to the first conversation message. The first reply message includes first content, which is generated by a model based on user requirements corresponding to the first conversation message. In response to receiving a collection request for the first content, the first content in the first reply message is added to the user's content collection page. In response to detecting a content viewing request, second content is presented in the content collection page, which is regenerated by the model based on user requirements.

[0042] Therefore, by providing a modular, simple-input conversational interaction solution, users can conveniently and quickly view the content of the digital assistant's historical replies, which can improve the interaction efficiency between users and digital assistants.

[0043] Some example embodiments of the present disclosure will be described in detail below with reference to the examples in the accompanying drawings. It should be understood that the pages shown in the accompanying drawings are merely examples, and a variety of page designs may exist. The various graphical elements in a page may have different arrangements and different visual representations, one or more elements may be omitted or replaced, and one or more other elements may also be present. The embodiments of the present disclosure are not limited in this respect.

[0044] The digital assistant creation process described in the embodiments of the present disclosure can be implemented on an application runtime platform, a terminal device installed with an application runtime platform, and / or a server corresponding to the assistant creation platform. In the following examples, for the purpose of discussion, the description is from the perspective of the application runtime platform, for example Figure 1 The application execution platform 140 is shown. The page presented by the application execution platform 140 can be presented via the terminal device of the user 145, and the user input can be received via the terminal device of the user 145.

[0045] Figure 2 Flowchart of information flow 200 of conversation interaction according to some embodiments of the present disclosure is shown. Information flow 200 involves client 201, server 202 and model service 203. Here, client 201 can be, for example, a client device of application running platform 140, and server 202 can be, for example, a server device of application running platform 140. Client 201, server 202 and model service 406 can correspond to Figure 1 For ease of discussion, reference will be made to the application runtime platform 140. Figure 1 The information flow 200 is described with reference to the environment 100 of FIG.

[0046] In an embodiment of the present disclosure, a digital assistant is used to interact with a user. The client 201 can present an interaction window between the user and the digital assistant in the client interface. The interaction window between the user and the digital assistant may include a conversation window, in which the interaction between the user and the digital assistant may be presented in the form of a conversation message. Alternatively or additionally, the interaction window between the user and the digital assistant may also include other types of windows, such as a window in a floating window mode, in which the user can trigger the digital assistant to perform corresponding operations by inputting instructions, selecting shortcut instructions, etc. As an intelligent assistant, the digital assistant has intelligent dialogue and information processing capabilities. In the interaction window, the user inputs an interaction message, and the digital assistant provides a reply message in response to the user input.

[0047] In some embodiments, the user can interact with the digital assistant by sending and / or receiving messages in the conversation window. The client 201 can, for example, determine that a conversation message from the user has been received in response to detecting text entered by the user in the input box. The client 201 can also, for example, collect user audio in response to detecting a user triggering operation (e.g., a click operation, a long press operation, etc.) on an audio control. The client 201 can determine the audio or the text content corresponding to the audio as the message content to be sent by the user (i.e., a conversation message from the user).

[0048] In information flow 200, during a conversation between a user and a digital assistant, client 201, in response to receiving a first conversation message from the user, sends (205) the first conversation message to server 202. Client 201 may, for example, send the first conversation message to server 202 via a communication connection with server 202.

[0049] In response to receiving the first session message, the server 202 passes (210) the first session message to the model service 203 to provide the first session message to the model. It is understood that the server 202 may not process the first session message but directly pass the received first session message to the model service 203.

[0050] As mentioned above, model service 203 can invoke one or more models, such as the capabilities of model 155. After receiving the first conversation message, model service 203 can invoke model 155 to process the first conversation message. Specifically, model 155 can determine the user requirement indicated by the first conversation message and, based at least on the user requirement, generate first content corresponding to the first conversation message. In some embodiments, model 155 can generate the first content based on the target data source and the user requirement. For example, if the user requirement indicates summarizing data in the target data source, model 155 can generate the first content based on the target data source and the user requirement. Model service 203 can send the processing results of the first conversation message to server 202.

[0051] In some embodiments, the model service 203 or the model 155 may also determine whether the first content is reusable content. If the first content is reusable (for example, the first content is a chart-type content), the model service 203 or the model 155 may also add a mark to the first content indicating that it is reusable. If the first content is not reusable (for example, the first content is ordinary text content), the model service 203 or the model 155 may add a mark to the first content indicating that it is not reusable, or may not add any mark to the first content. In some embodiments, the model service 203 or the model 155 may not need to determine whether the first content is reusable. In such a case, it can be assumed that all content determined based on user needs is reusable.

[0052] The server 202 may receive (215) a processing result for the first conversation message from the model service 203, and the processing result may include, for example, an indication of the first content and a mark indicating whether the first content is reusable. The server 202 sends (220) the processing result to the client 201. In response to receiving the processing result, the client 201 may determine whether the processing result includes a mark indicating that the first content is reusable. If the processing result includes a mark indicating that the first content is reusable, the client 201 may present a first reply message of the digital assistant to the first conversation message in the conversation between the user and the digital assistant, and the first reply message includes the first content. Figure 3 An example 300 of a client interface for conversational interaction according to some embodiments of the present disclosure is shown. Figure 3 As shown, in example 300, the main conversation window between the digital assistant (shown as "XX Assistant" in the figure) and the user is presented in area 310. The digital assistant can be regarded as one of the user's contacts and is presented in the information flow of the instant messaging application, and the information flow is presented in area 320 of example 300. The user selects the digital assistant in the instant messaging application to enter the main conversation window. The client 201 can present the first reply message 301 (for example, a reply message from "XX Assistant") in the main conversation window. The first reply message 301 is presented with the first content. For example, the client 201 can determine that a collection request for the first content in the first reply message is detected in response to detecting a click operation on the first reply message. The client 201 can also determine that a collection request for the first content in the first reply message is detected in response to receiving a conversation message sent by the user indicating that the first content is to be added to the user's content collection page (for example, a voice or text message "Collect first content"). In response to detecting a collection request for the first content in the first reply message, the client 201 may add the first content in the first reply message to the user's content collection page (eg, a data dashboard).

[0053] In some embodiments, the first reply message 301 may further include an operation control for the first content, such as a favorites control 302. In response to detecting a triggering operation (e.g., a click operation, a double-click operation, a long press operation, etc., depending on the application configuration) on the favorites control 302 in the first reply message, the client 201 may determine that a triggering operation for the favorites control 302 has been received. In response to receiving the triggering operation for the favorites control 302, the client 201 may add the first content in the first reply message to the user's content favorites page.

[0054] Alternatively or additionally, although the user-triggered save operation is for the first content or the first reply message, in embodiments of the present disclosure, the content saved on the content save page is the user's need (or user intent) corresponding to the first reply message. This user need can be determined based on the first conversation message (and possibly also contextual content related to the first conversation message). This save operation allows the saved content to be updated on the content save page when a subsequent view or update operation is triggered, displaying updated content that matches the saved user need.

[0055] Return Reference Figure 2 In some embodiments, the client 201 may send (225) an add request to the server 202, indicating that the first content should be added to the user's content collection page. In response to the add request, the server 202 adds the first content to the user's content collection page. In response to completing the addition, the server 202 may send (230) a message to the client 201 indicating that the addition was successful.

[0056] In some embodiments, in response to receiving the message indicating that the addition is successful (i.e., in response to the first content being added to the user's content collection page), the client 201 may present a prompt message in the session indicating that the first content has been added to the content collection page. The prompt message may include, for example, an entry indication for the content collection page. In this way, the user can know where to view the collection content later. In some embodiments, the entry indication in the prompt message may include an entry control, and by triggering the entry control, the user can jump to the content collection page. For example, the client 201 may determine that a content viewing request has been received in response to detecting a triggering operation on the entry control. For example, as Figure 3 As shown, the client 201 may present a prompt message 303. The prompt message 303 may include the entry control "My XX Board". For example, the client 201 may determine that a content viewing request has been received in response to detecting a trigger operation on the entry control "My XX Board".

[0057] Alternatively or additionally, in some embodiments, client 201 may determine that a content viewing request has been received in response to receiving a session message from the user instructing to view the first content. In some embodiments, client 201 may also present an operation control for the content collection page in an area outside of the session (e.g., a function area). Client 201 may determine that a content viewing request has been received in response to detecting a triggering operation on the operation control.

[0058] In response to detecting the content viewing request, client 201 presents second content on the content collection page. The second content is regenerated by the model based on the user's needs. The second content can, for example, be content generated based on the latest target data source. In other words, if the target data source has not been updated, the second content and the first content may include the same content. If the target data source is updated, the second content generated based on the updated target data source may be different from the first content.

[0059] Regarding the specific method of presenting the second content, in some embodiments, the client 201 can automatically generate the second content in response to detecting the content viewing request, and present the second content in the content collection page. Specifically, the client 201 can send (235) a rendering message to the server 202 in response to the content viewing request, indicating that the content collection page is to be presented. In response to receiving the rendering message, the server 202 provides (240) an identifier of the user demand corresponding to the first session message to the model service 203. The model service 203 can determine the second content to be presented based on the identifier and send (245) an indication of the second content to the server 150. In response to the indication, the server 150 can send (250) a rendering message to the client 201 in response to the rendering message, indicating that the content collection page is to be rendered. The rendering message can, for example, include the second content. In response to receiving the rendering message, the client 201 renders the content collection page based on the rendering message. The rendered content collection page presents the second content.

[0060] In some embodiments, client 201 can also automatically present the first content on the content collection page in response to detecting a content viewing request. In some embodiments, client 201 can generate second content in response to a preset content generation strategy and replace the first content presented on the content collection page with the second content. In some embodiments, the preset content generation strategy can, for example, be periodic generation at a preset execution interval and / or in response to an update of a data source associated with a user's request. Specifically, client 201 can, in response to receiving a content viewing request, present the previously added first content on the content collection page by default. For example, client 201 can present a display area corresponding to the first content and present the first content in the display area. Furthermore, to allow the user to view content generated based on the latest target data source on the content collection page, client 201 can also, in response to detecting an update request for the first content, present the second content, regenerated based on the updated target data source, in the display area. Regarding the specific method of detecting an update request, in some embodiments, client 201 can present an update control in the display area corresponding to the first content. In response to detecting a trigger operation on the update control, client 201 may determine that an update request for the first content has been detected, and present the second content regenerated based on the updated target data source in the display area. In some embodiments, client 201 may also determine that an update request for the first content has been detected, and present the second content regenerated based on the updated target data source in the display area, in response to receiving user input indicating an update of the first content and presentation of the second content (e.g., text "update first content and present update result").

[0061] For example, the client 201 may present a display area corresponding to the second content and present the second content in the display area. The display area corresponding to the second content and the display area corresponding to the first content may be the same display area. In this case, the client 201 may, for example, send a first rendering message to the server 202 in response to receiving a content viewing request, and receive from the server 202 a first rendering message including the first content, or an instruction to render the first content. The client 201 may further send a second rendering message to the server 202 in response to detecting a trigger operation on the update control, and receive from the server 202 a second rendering message including the second content.

[0062] In some embodiments, client 201 may also, in response to detecting a content viewing request, directly present the second content generated based on the updated target data source on the content collection page. For example, client 201 may present a display area corresponding to the second content and present the second content in the display area. In this case, client 201 may, for example, send a presentation message to server 202 instructing it to present the content collection page in response to detecting a content viewing request, and directly receive a rendering message from server 202 including the second content.

[0063] In some embodiments, the content collection page may include at least one chart type and / or at least one form type of content. Figure 4 An example 400 of a content collection page according to some embodiments of the present disclosure is shown. Figure 4 As shown, in example 400 , a plurality of contents may be presented, and the plurality of contents may include chart-type contents and form-type contents.

[0064] In some embodiments, the client 201 may present at least a portion of the first conversation message in the display area corresponding to the first content or the second content on the content collection page. For example, the client 201 may determine the message content in the first conversation message that indicates the user's needs and present this portion of the message content in the display area. The message content may be determined by the client 201 and / or the server 202 (i.e., the application running platform 140) itself, or may be determined with the help of a model provided by the model service 203. For example, Figure 4 As shown, for the display area 410 , if the display area 410 is the display area corresponding to the first content or the second content, the client 201 may present a message 401 from the user in the display area 410 , and the message 401 may be at least a portion of the first conversation message.

[0065] In some embodiments, the client 201 may also present the generation time of the second content in association with the second content. Figure 4 As shown, the client 201 may also present a generation time 402 in the display area 410. The generation time 402 may be used to indicate the generation time of the second content.

[0066] Because the target data source can be updated multiple times, and different second content can be obtained based on different updated versions of the target data source, in some embodiments, to facilitate users in viewing different historical versions of the second content, client 201 may also present a version viewing portal associated with the second content. For example, in response to detecting a trigger on the version viewing portal, client 201 may present one or more version options corresponding to the second content. Each version option corresponds to a historical version of the content generated by the model based on user needs.

[0067] In some embodiments, for the collected content on the content collection page, the method of triggering the collection content update can be manually triggered by the user, or can be actively triggered according to a certain strategy (for example, timed triggering, or triggering in response to a change in the target data source associated with the user's needs). Optionally or additionally, each updated content can be saved as a corresponding version for subsequent viewing by the user.

[0068] In some embodiments, the client 201 may also present the conversation between the user and the digital assistant in response to detecting a call to the digital assistant in the content collection page. For example, the client 201 may determine that a call to the digital assistant is detected and present the conversation between the user and the digital assistant in response to receiving user input in the content collection page indicating the presentation of the conversation between the user and the digital assistant (for example, receiving the user's voice or text instruction "open a conversation with the digital assistant") In some embodiments, in order to facilitate the user to switch to the conversation with the digital assistant in the content collection page, the client 201 may also provide a call-up control for the digital assistant in the presentation area of ​​the content collection page. The client 201 may determine that a call-up request to the digital assistant is detected in response to triggering the call-up control, and present the conversation between the user and the digital assistant.

[0069] For example, Figure 4 As shown, the client 201 may also be presented with a call-up control 403 in example 400. For example, the client 201 may switch to presenting the main conversation window between the user and the digital assistant (eg, Figure 3 The client 201 may also directly invoke the digital assistant in example 400 in response to triggering the invocation control 403 and display a sub-session window in which the user interacts with the digital assistant. The client 201 may then present the conversation between the user and the digital assistant in the sub-session window.

[0070] In some embodiments, the client 201 may also present the details of the second content in response to receiving the detail viewing operation. For example, the client 201 may determine that the detail viewing operation has been received in response to a click operation on the display area for presenting the second content. Figure 4 As shown, the client 201 may, for example, determine that a detail viewing operation for the second content corresponding to the display area 410 has been received in response to detecting a click operation on the display area 410 .

[0071] In response to receiving the detail viewing operation, the client 201 may send (255) a detail presentation message to the server 202 indicating that the detailed content of the second content is to be presented. The client 201 may then present the detailed content of the second content in response to receiving (260) a detail rendering message from the server 202 indicating that the detailed content is to be rendered. For example, the client 201 may switch from a content collection page to a content viewing page corresponding to the second content, and present the detailed content of the second content in the content viewing page. Alternatively or additionally, the client 201 may also directly present the detailed content of the second content in the content collection page, which is not limited in the present disclosure.

[0072] In summary, according to the embodiments of the present disclosure, a modular, simple-input conversation interaction solution can be provided to allow users to conveniently and quickly view the content of the digital assistant's historical replies, thereby improving the interaction efficiency between users and digital assistants.

[0073] Figure 5 FIG. 5 is a flow chart showing a process 500 for session interaction according to some embodiments of the present disclosure. The process 500 may be implemented at the application execution platform 140. Figure 1 Process 500 is described.

[0074] In box 510, in response to receiving a first conversation message from the user in the conversation between the user and the digital assistant, the application running platform 140 presents a first reply message of the digital assistant to the first conversation message, where the first reply message includes first content, and the first content is generated by the model based on the user needs corresponding to the first conversation message.

[0075] In block 520 , in response to receiving the collection request for the first content, the application execution platform 140 adds the first content in the first reply message to the user's content collection page.

[0076] In block 530 , in response to detecting the content viewing request, the application execution platform 140 presents the second content in the content collection page, where the second content is regenerated by the model based on user demand.

[0077] In some embodiments, the first reply message includes a favorite control for the first content, and wherein the favorite request is based on triggering of the favorite control.

[0078] In some embodiments, the first content is generated based on a target data source, and wherein the target data source has been updated when the content viewing request is detected, the second content is regenerated based on the updated target data source.

[0079] In some embodiments, presenting the first reply message includes: providing the first conversation message to the model; receiving a processing result for the first conversation message from the model, the processing result including an indication of the first content and a mark indicating whether the first content is reusable; and in response to determining that the processing result includes the mark indicating that the first content is reusable, presenting the first reply message including the first content.

[0080] In some embodiments, presenting the second content includes: providing an identification of a user need corresponding to the first conversation message to the model; and receiving an indication of the second content from the model.

[0081] In some embodiments, the regeneration of the second content is in response to at least one of the following: in response to detecting a content viewing request, in response to a preset content generation strategy. In some embodiments, the preset content generation strategy may be, for example, periodic generation at a preset execution interval, and / or in response to an update of a data source associated with a user request.

[0082] In some embodiments, the process 500 further includes: presenting a prompt message in the session indicating that the first content is added to the content collection page, the prompt message including an entry indication to the content collection page.

[0083] In some embodiments, presenting the second content includes: presenting the second content on the content collection page in response to detecting a triggering operation on the content collection page.

[0084] In some embodiments, presenting the second content includes: presenting a content collection page, the content collection page including at least a display area corresponding to the first content; and in response to detecting an update request for the first content, presenting the second content in the display area.

[0085] In some embodiments, the process 500 further includes: presenting at least a portion of the first conversation message in a display area corresponding to the first content or the second content on the content collection page.

[0086] In some embodiments, process 500 further includes presenting a generation time of the second content in association with the second content.

[0087] In some embodiments, process 500 also includes: presenting a version viewing portal in association with the second content; and in response to detecting a trigger for the version viewing portal, presenting one or more version options corresponding to the second content, each version option corresponding to a historical version of the content generated by the model based on user needs.

[0088] In some embodiments, process 500 further includes, in response to detecting a request to invoke the digital assistant in the content collection page, presenting a conversation between the user and the digital assistant.

[0089] In some embodiments, a call-up control for the digital assistant is provided in the presentation area of ​​the content collection page, and the call-up request is based on triggering the call-up control.

[0090] In some embodiments, the content collection page includes at least one of the following types of content: at least one chart type, and at least one form type.

[0091] Figure 6 A schematic structural block diagram of an apparatus 600 for conversation interaction according to some embodiments of the present disclosure is shown. The apparatus 600 may be implemented in or included in the application execution platform 140, for example. Each module / component in the apparatus 600 may be implemented by hardware, software, firmware, or any combination thereof.

[0092] As shown in the figure, the device 600 includes a message presentation module 610, which is configured to present the digital assistant's first reply message to the first conversation message in response to receiving the user's first conversation message in a conversation between the user and the digital assistant. The first reply message includes first content, and the first content is generated by the model based on the user's needs corresponding to the first conversation message. The device 600 also includes a content addition module 620, which is configured to add the first content in the message to the user's content collection page in response to receiving a collection request for the first content. The device 600 also includes a content presentation module 630, which is configured to present second content in the content collection page in response to detecting a content viewing request. The second content is regenerated by the model based on user needs.

[0093] In some embodiments, the first reply message includes a favorite control for the first content, and wherein the favorite request is based on triggering of the favorite control.

[0094] In some embodiments, the first content is generated based on a target data source, and wherein the target data source has been updated when the content viewing request is detected, the second content is regenerated based on the updated target data source.

[0095] In some embodiments, the message presentation module 610 is further configured to: provide a first conversation message to the model; receive a processing result for the first conversation message from the model, the processing result including an indication of the first content and a mark indicating whether the first content is reusable; and in response to determining that the processing result includes a mark indicating that the first content is reusable, present a first reply message including the first content.

[0096] In some embodiments, the content presentation module 630 is further configured to: provide the model with an identification of the user demand corresponding to the first conversation message; and receive an indication of the second content from the model.

[0097] In some embodiments, the regeneration of the second content is in response to at least one of the following: in response to detecting a content viewing request, in response to a preset content generation strategy.

[0098] In some embodiments, the apparatus 600 further includes: a prompt message presenting module configured to present a prompt message in the session indicating that the first content is added to the content collection page, wherein the prompt message includes an entry indication for the content collection page.

[0099] In some embodiments, the content presentation module 630 is further configured to: in response to detecting a triggering operation on the content collection page, present the second content on the content collection page.

[0100] In some embodiments, the content presentation module 630 is further configured to: present a content collection page, the content collection page including at least a display area corresponding to the first content; and present the second content in the display area in response to detecting an update request for the first content.

[0101] In some embodiments, the apparatus 600 further includes: a conversation message presentation module configured to present at least a portion of the first conversation message in a presentation area corresponding to the first content or the second content in the content collection page.

[0102] In some embodiments, the apparatus 600 further includes: a generation time presentation module configured to present the generation time of the second content in association with the second content.

[0103] In some embodiments, the device 600 also includes: a version entry presentation module, configured to present a version viewing entry in association with the second content; and a historical version presentation module, configured to present one or more version options corresponding to the second content in response to detecting a trigger on the version viewing entry, each version option corresponding to a historical version of the content generated by the model based on user needs.

[0104] In some embodiments, the device 600 further includes: a conversation presentation module configured to present a conversation between the user and the digital assistant in response to detecting a request to invoke the digital assistant in the content collection page.

[0105] In some embodiments, a call-up control for the digital assistant is provided in the presentation area of ​​the content collection page, and the call-up request is based on triggering the call-up control.

[0106] In some embodiments, the content collection page includes at least one of the following types of content: at least one chart type, and at least one form type.

[0107] Figure 71 shows a block diagram of an electronic device 700 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 7 The illustrated electronic device 700 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 7 The electronic device 700 shown may include or be implemented as Figure 1 application execution platform 140, or Figure 6 device 600.

[0108] like Figure 7 As shown, electronic device 700 is in the form of a general electronic device. Components of electronic device 700 may include, but are not limited to, one or more processors or processing units 710, memory 720, storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. Processing unit 710 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 720. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to increase the parallel processing capabilities of electronic device 700.

[0109] The electronic device 700 typically includes a plurality of computer storage media. Such media can be any accessible media that can be obtained by the electronic device 700, including but not limited to 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 medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 700.

[0110] The electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 7 As shown in FIG, a magnetic 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 may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 720 may include a computer program product 725 having one or more program modules configured to perform the various methods or actions of various embodiments of the present disclosure.

[0111] The communication unit 740 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 700 can be implemented as a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 700 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0112] Input device 750 may be one or more input devices, such as a mouse, keyboard, or trackball. Output device 760 may be one or more output devices, such as a display, a speaker, or a printer. Electronic device 700 may also communicate with one or more external devices (not shown) via communication unit 740 as needed, such as storage devices, display devices, or the like, with one or more devices that allow a user to interact with electronic device 700, or with any device that allows electronic device 700 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0113] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0114] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0115] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0116] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0117] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0118] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not 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 selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for conversation interaction, comprising: In a conversation between a user and a digital assistant, in response to receiving a first conversation message from the user, presenting a first reply message from the digital assistant to the first conversation message, where the first reply message includes first content, where the first content is generated by a model based on a user demand corresponding to the first conversation message; In response to receiving a collection request for the first content, adding the first content and the user requirement in the first reply message to a content collection page of the user; as well as In response to detecting a content viewing request, second content matching the user requirement is presented in the content collection page, where the second content is regenerated by the model based on the user requirement in response to detecting at least one of the content viewing request and a preset content generation strategy. 2 . The method of claim 1 , wherein the first reply message includes a favorite control for the first content, and wherein the favorite request is based on triggering of the favorite control. 3 . The method according to claim 1 , wherein the first content is generated based on a target data source, and wherein the target data source has been updated when the content viewing request is detected, and the second content is regenerated based on the updated target data source.

4. The method of claim 1 , wherein presenting the first reply message comprises: providing the first session message to the model; receiving, from the model, a processing result for the first conversation message, the processing result including an indication of the first content and a flag indicating whether the first content is reusable; as well as In response to determining that the processing result includes the mark indicating that the first content is reusable, presenting the first reply message including the first content.

5. The method of claim 1 , wherein presenting the second content comprises: providing the model with an identifier of the user requirement corresponding to the first conversation message; as well as An indication of the second content is received from the model.

6. The method according to claim 1, further comprising: A prompt message is presented in the session, indicating that the first content is added to the content collection page, wherein the prompt message includes an entry indication for the content collection page.

7. The method of claim 1 , wherein presenting the second content comprises: In response to detecting a triggering operation on the content collection page, presenting the second content on the content collection page.

8. The method of claim 1 , wherein presenting the second content comprises: Presenting the content collection page, wherein the content collection page at least includes a display area corresponding to the first content; as well as In response to detecting an update request for the first content, presenting the second content in the presentation area.

9. The method according to claim 1, further comprising: At least a portion of the first conversation message is presented in a display area corresponding to the first content or the second content on the content collection page.

10. The method according to claim 1, further comprising: A generation time of the second content is presented in association with the second content.

11. The method according to claim 1 , further comprising: presenting a version viewing entrance in association with the second content; as well as In response to detecting a trigger on the version viewing portal, one or more version options corresponding to the second content are presented, each version option corresponding to a historical version of the content generated by the model based on the user demand.

12. The method according to claim 1, further comprising: In response to detecting a request to invoke the digital assistant in the content collection page, presenting a conversation between the user and the digital assistant.

13. The method according to claim 12, wherein a call-up control for the digital assistant is provided in a presentation area of ​​the content collection page, and the call-up request is based on triggering the call-up control.

14. The method according to claim 1, wherein the content collection page includes at least one of the following types of content: At least one chart type, At least one form type.

15. A device for conversation interaction, comprising: a message presentation module configured to, in a conversation between a user and a digital assistant, in response to receiving a first conversation message from the user, present a first reply message from the digital assistant to the first conversation message, the first reply message including first content generated by a model based on a user demand corresponding to the first conversation message; a content adding module, configured to, in response to receiving a collection request for the first content, add the first content and the user requirement in the first reply message to the user's content collection page; as well as The content presentation module is configured to present second content matching the user demand in the content collection page in response to detecting a content viewing request, wherein the second content is regenerated by the model based on the user demand in response to detecting at least one of the content viewing request and a preset content generation strategy.

16. An electronic device comprising: at least one processing unit; as well as At least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 14 when executed by the at least one processing unit.

17. A computer-readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the method according to any one of claims 1 to 14.

Images