Method, apparatus, device and storage medium for message processing

Abstract

According to embodiments of the present disclosure, methods, apparatuses, devices and storage media for message processing are provided. In one method, recommendation information associated with a target object is obtained; and based on the recommendation information, recommendation content is provided to the target object, wherein the recommendation content at least includes a first part corresponding to a first message classification, the first part including a first group of content items corresponding to the first message classification, wherein the first group of content items indicates a first group of conversations corresponding to the first message classification, and first description information about unread messages in the first group of conversations, wherein the first message classification is determined based on a first degree of association between the unread messages in the first group of conversations and a current work of the target object, or the first message classification is determined based on time information of the unread messages in the first group of conversations. Thus, embodiments of the present disclosure can sort unread messages according to the degree of relevance to work or time information, thereby improving the efficiency of message acquisition.

Description

TECHNICAL FIELD

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and in particular, to a method, apparatus, device and computer readable storage medium for message processing. BACKGROUND

[0002] With the rapid development of Internet technology, the Internet has become an important platform for people to obtain and share content. Users can access the Internet through terminal devices to enjoy various Internet services. In the Internet platform, people can obtain various types of messages, and how to effectively process messages has become the focus of attention. SUMMARY

[0003] In a first aspect of the present disclosure, a method for message processing is provided. The method comprises: obtaining recommendation information associated with a target object; and providing recommendation content to the target object based on the recommendation information, wherein the recommendation content at least includes a first part corresponding to a first message classification, the first part includes a first group of content items corresponding to the first message classification, wherein the first group of content items indicates a first group of conversations corresponding to the first message classification, and first description information about unread messages in the first group of conversations, wherein the first message classification is determined based on a first degree of association between the unread messages in the first group of conversations and a current work of the target object, or the first message classification is determined based on time information of the unread messages in the first group of conversations.

[0004] In a second aspect of the present disclosure, a method for message processing is provided. The method comprises: providing at least one scene in an interaction window of a target object and a digital assistant, the at least one scene including a first scene; wherein the first scene is configured with corresponding configuration information to perform a task related to processing unread messages, the configuration information including at least one of: scene setting information for describing information related to processing unread messages, and plug-in information indicating at least one plug-in for performing a task related to processing unread messages; and in response to a preset operation of the target object on the first scene, performing an interaction between the target object and the digital assistant based at least on the configuration information of the first scene.

[0005] In a third aspect of the present disclosure, an apparatus for message processing is provided. The apparatus includes an information obtaining module configured to obtain recommendation information associated with a target object; and a content providing module configured to provide, based on the recommendation information, a recommendation content to the target object, wherein the recommendation content comprises at least a first part corresponding to a first message category, the first part comprising a first group of content items corresponding to the first message category, wherein the first group of content items indicates a first group of conversations corresponding to the first message category, and first description information about unread messages in the first group of conversations, wherein the first message category is determined based on a first degree of association between the unread messages in the first group of conversations and a current work of the target object, or the first message category is determined based on time information of the unread messages in the first group of conversations.

[0006] In a fourth aspect of the present disclosure, an apparatus for message processing is provided. The apparatus includes a scene providing module configured to provide at least one scene in an interaction window of a target object and a digital assistant, the at least one scene comprising a first scene; wherein the first scene is configured with corresponding configuration information to perform a task related to processing unread messages, the configuration information comprising at least one of scene setting information and plug-in information, wherein the scene setting information is used to describe information related to processing unread messages, and the plug-in information indicates at least one plug-in used to perform the task related to processing unread messages; and an interaction module configured to perform, in response to a preset operation of the target object on the first scene, an interaction between the target object and the digital assistant based at least on the configuration information of the first scene.

[0007] In a fifth 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. The instructions, when executed by the at least one processing unit, cause the device to perform the method of the first aspect or the second aspect.

[0008] In a sixth aspect of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium has stored thereon a computer program, which is executable by a processor to implement the method of the first aspect or the second aspect.

[0009] 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 used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

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

[0011] FIG. 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented is shown;

[0012] FIG. 2 A flowchart showing a method for message processing according to some embodiments of the present disclosure is shown;

[0013] FIGS. 3A-3C An example interface according to some embodiments of the present disclosure is shown;

[0014] FIG. 4 An example interface according to some embodiments of the present disclosure is shown;

[0015] FIG. 5 A flowchart showing a method for message processing according to some embodiments of the present disclosure is shown;

[0016] FIGS. 6A-6C An example interface according to some embodiments of the present disclosure is shown;

[0017] FIG. 7A FIG. 7B A block diagram of an apparatus for message processing according to some embodiments of the present disclosure is shown; and

[0018] FIG. 8 A block diagram of an apparatus capable of implementing a plurality of embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0019] It can be understood that, before using the technical solutions disclosed in the embodiments of the present disclosure, the type of information involved in the present disclosure, the scope of use, the use scenario, etc. should be informed to the relevant user and the authorization of the relevant user should be obtained by appropriate means in accordance with relevant laws and regulations. Among them, the relevant user can include any type of right subject, such as an individual, an enterprise, or a group.

[0020] For example, in response to receiving the active request of the user, the prompt information is sent to the relevant user to explicitly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user. Thus, the relevant user can voluntarily choose whether to provide information to the electronic device, application program, server or storage medium, etc. software or hardware that performs the operation of the technical solutions of the present disclosure according to the prompt information.

[0021] As an optional but non-limiting implementation manner, in response to receiving the active request of the relevant user, the manner of sending prompt information to the relevant user may, for example, be a pop-up window manner, and the prompt information can be presented in the form of text in the pop-up window. In addition, the pop-up window can also carry a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0022] It can be understood that the above notification and user authorization obtaining process is only illustrative, and does not limit the implementation of the present disclosure, and other ways meeting relevant laws and regulations can also be applied to the implementation of the present disclosure.

[0023] It can be understood that, when the technical solution is adopted, the data involved (including but not limited to the data itself, acquisition, use, storage, and transmission of the data) should comply with the requirements of relevant laws and regulations and relevant provisions.

[0024] The term "in response to" as used herein refers to a state in which a corresponding event occurs or a condition is met. It will be understood that the timing of the execution of the subsequent action performed in response to the event or condition is not necessarily strongly associated with the time at which the event occurs or the condition is established. For example, in some cases, the subsequent action can be performed immediately upon the occurrence of the event or the establishment of the condition; in other cases, the subsequent action can be performed after a period of time has elapsed since the occurrence of the event or the establishment of the condition.

[0025] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms, and should not be construed as being limited to the embodiments set forth herein, but rather, the embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for exemplary purposes only, and are not intended to limit the scope of protection of the present disclosure.

[0026] It should be noted that the titles of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment can be included under any section / subsection. Furthermore, embodiments described in any section / subsection can be combined with any other embodiment described in the same section / subsection and / or a different section / subsection in any manner.

[0027] In the description of embodiments of the present disclosure, the term "comprising" and similar terms are to be interpreted as open-ended, i.e., "including but not limited to". The term "based on" is to be interpreted as "based, at least in part, on". The term "one embodiment" or "the embodiment" is to be interpreted as "at least one embodiment". The term "some embodiments" is to be interpreted as "at least some embodiments". Other explicit and implicit definitions can also be included below. The terms "first", "second", etc. can refer to different or same objects. Other explicit and implicit definitions can also be included below.

[0028] As used herein, the term “model” can learn the association between the corresponding input and output from the training data, so that the corresponding output can be generated for a given input after the training is completed. The generation and use of the model can be based on the technology allowed by laws and regulations, referred to as available technology. By way of example, deep learning is a machine learning algorithm that processes input and provides a corresponding output by using multiple layers of processing units. In this document, “model” can also be referred to as “machine learning model”, “machine learning network” or “network”, which are used interchangeably herein. One model can also include different types of processing units or networks.

[0029] As briefly mentioned above, in the Internet platform, people can obtain various types of messages, which leads to the fact that people can need to process a large number of unread messages. Therefore, how to improve the processing efficiency of unread messages becomes the focus of attention.

[0030] Embodiments of the present disclosure provide a scheme for message processing. Specifically, recommendation information associated with a target object can be obtained. Further, based on the recommendation information, a target object can be provided with recommendation content, wherein the recommendation content at least includes a first part corresponding to a first message classification, and the first part includes a first group of content items corresponding to the first message classification, wherein the first group of content items indicates a first group of conversations corresponding to the first message classification, and first description information about unread messages in the first group of conversations, wherein the first message classification is determined based on a first degree of association between the unread messages in the first group of conversations and the current work of the target object, or the first message classification is determined based on time information of the unread messages in the first group of conversations. Thus, embodiments of the present disclosure can sort unread messages according to the degree of relevance to work or time information, thereby improving the efficiency of message acquisition.

[0031] Example embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0032] Example Environment

[0033] FIG. 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. In this example environment 100, a digital assistant 120 and an application 125 are installed in a terminal device 110. A target object 140 can interact with the digital assistant 120 and the application 125 via the terminal device 110 and / or an attached device of the terminal device 110.

[0034] In some embodiments, the digital assistant 120 and the application 125 can be downloaded and installed in the terminal device 110. In some embodiments, the digital assistant 120 and the application 125 can also be accessed by other means, such as accessed through a web page, etc. In some embodiments, the digital assistant 120 and the application 125 can be implemented by a server, and the terminal device 110 can access the digital assistant 120 and the application 125 through the server.FIG. 1 In environment 100, in response to application 125 being launched, terminal device 110 can present the interface 150 of digital assistant 120 and application 125.

[0035] Applications 125 include, but are not limited to, one or more of the following: chat applications (also known as instant messaging applications), document applications, audio and video conferencing applications, email applications, task applications, calendar applications, goal and key results (OKR) applications, etc. Although FIG. 1 The image shows a single application, but in reality, multiple applications can be installed on the terminal device 110. In some embodiments, application 125 may include a multi-functional collaboration platform, such as an office collaboration platform (also known as an office suite) that can provide integration of various types of business components, such as chat components, document components, calendar components, audio and video conferencing components, etc., to facilitate people's office work, communication, and other activities. In a multi-functional collaboration platform, people can launch different business components as needed to complete corresponding information processing, sharing, communication, etc.

[0036] Application 125 can provide content entity 126. Content entity 126 can be a content instance created on application 125 by target object 140 or other users. For example, depending on the type of application 125, content entity 126 can be a document (e.g., a Word document, a PDF document, a presentation, a spreadsheet, etc.), email, message (e.g., a conversational message on an instant messaging application), calendar, schedule, task, audio, video, image, etc.

[0037] In some embodiments, the digital assistant 120 may be provided by a standalone application or may be integrated into an application 120 capable of providing content entities. The application providing the client interface for the digital assistant may correspond to a single-function application or a multi-functional collaboration platform, such as an office suite or other collaboration platforms capable of integrating multiple components. In some embodiments, the digital assistant 120 supports the use of plugins. Each plugin can provide one or more functions of an application or business component. Such plugins include, but are not limited to, one or more of the following: search plugins, contact plugins, messaging plugins, document plugins, form plugins, email plugins, calendar plugins, schedule plugins, task plugins, etc.

[0038] Digital assistant 120 is a user's intelligent assistant, possessing intelligent dialogue and information processing capabilities. In embodiments of this disclosure, digital assistant 120 is used to interact with target object 140 to assist target object 140 in using terminal devices or applications. An interaction window with digital assistant 120 can be presented in the client interface. In the interaction window, target object 140 can converse with digital assistant 120 by inputting natural language to instruct digital assistant to assist in completing various tasks, including operations on content entity 126.

[0039] In some embodiments, the digital assistant 120 can be included in a contact list of the current target object 140 in an office suite as a contact of the target object 140, or be included in an information stream of a chat component. In some embodiments, the target object 140 has a corresponding relationship with the digital assistant 120. For example, a first digital assistant corresponds to a first user, a second digital assistant corresponds to a second user, and so on. In some embodiments, the first digital assistant can uniquely correspond to the first user, the second digital assistant can uniquely correspond to the second user, and so on. That is, the first digital assistant of the first user can be specific or exclusive to the first user. For example, in the process of the first digital assistant providing assistance or services for the first user, the first digital assistant can utilize historical interaction information thereof with the first user, data authorized by the first user that it can access, a current interaction context thereof with the first user, and the like. If the first user is an individual or a person, the first digital assistant can be regarded as a personal digital assistant. It can be understood that in the disclosed embodiments, the first digital assistant is granted access to the data based on authorization of the first user. It should be understood that the “unique correspondence” or similar expressions in the present disclosure are not intended to limit the first digital assistant to be updated accordingly based on the interaction process between the first user and the first digital assistant. Of course, depending on the actual application needs, the digital assistant 120 does not necessarily have to be specific to the current target object 140, but can be a general digital assistant.

[0040] In some embodiments, multiple interaction modes of the target object 140 and the digital assistant 120 can be provided, and flexible switching between the multiple interaction modes can be provided. In the case that a certain interaction mode is triggered, a corresponding interaction area is presented to facilitate the interaction of the target object 140 and the digital assistant 120. The interaction of the target object 140 and the digital assistant 120 is different in different interaction modes, so that the interaction needs in different application scenarios can be flexibly adapted.

[0041] In some embodiments, information processing services specific to the target object 140 can be provided based on historical interaction information of the target object 140 and the digital assistant 120 and / or a data range specific to the target object 140. In some embodiments, the historical interaction information of the target object 140 interacting with the digital assistant 120 in multiple interaction modes respectively can be all stored in association with the target object 140. In this way, in one of the multiple interaction modes (any one or a specified one), the digital assistant 120 can provide services for the target object 140 based on the historical interaction information stored in association with the target object 140.

[0042] The digital assistant 120 can be invoked or woken up by appropriate means (e.g., a shortcut key, a button, or a voice) to present an interaction window with the target object 140. By selecting the digital assistant 120, an interaction window with the digital assistant 120 can be opened. The interaction window can include interface elements for information interaction, such as an input box, a message list, a message bubble, and the like. In other embodiments, the digital assistant 120 can be invoked by an entry control or a menu provided in a page, or can be invoked by inputting a preset instruction.

[0043] The interaction window of the digital assistant 120 with the target object 140 can include a conversation window, such as a conversation window in an instant messaging application or an instant messaging module of the target application. In some embodiments, the interaction window of the digital assistant 120 with the target object 140 can include a floating window corresponding to the digital assistant.

[0044] In some embodiments, the digital assistant 120 can support an interaction mode of a conversation window, also referred to as a conversation mode. In the interaction mode, a conversation window of the target object 140 with the digital assistant 120 is presented, and the target object 140 and the digital assistant 120 interact through conversation messages in the conversation window. In the conversation mode, the digital assistant 120 can perform a task according to the conversation messages in the conversation window.

[0045] In some embodiments, the conversation mode of the target object 140 with the digital assistant 120 can be invoked or woken up by appropriate means (e.g., a shortcut key, a button, or a voice) to present a conversation window. By selecting the digital assistant 120, a conversation window with the digital assistant 120 can be opened. The conversation window can include interface elements for information interaction, such as an input box, a message list, a message bubble, and the like.

[0046] In some embodiments, the digital assistant 120 can support an interaction mode of a floating window (or a floating window), also referred to as a floating window mode. In the case where the floating window mode is triggered, an operation panel (also referred to as a floating window) corresponding to the digital assistant 120 is presented, and the target object 140 can issue an instruction to the digital assistant 120 based on the operation panel. In some embodiments, the operation panel can include at least one candidate shortcut instruction. Alternatively or additionally, the operation panel can include an input control for receiving an instruction. In the floating window mode, the digital assistant 120 can perform a task according to the instruction issued by the target object 140 through the operation panel.

[0047] In some embodiments, the target object 140 and the floating window mode of the digital assistant 120 can also be invoked or woken up by appropriate means (e.g., shortcut key, button or voice) to present the corresponding operation panel. In some embodiments, the wake up of the digital assistant 120 can be supported in a specific application, e.g., in a document business component, to provide the interaction of the floating window mode. In some embodiments, to trigger the floating window mode to present the corresponding operation panel of the digital assistant 120, an entry control for the digital assistant 120 can be presented in the application interface. In response to detecting the triggering operation for the entry control, it can be determined that the floating window mode is triggered, and the corresponding operation panel of the digital assistant 120 is presented in the target interface region.

[0048] In some embodiments described below, for the convenience of discussion, the interaction window of the user with the digital assistant is mainly taken as an example of the conversation window.

[0049] In some embodiments, the terminal device 110 communicates with the server 130 to implement the provision of the services of the digital assistant 120 and the application 125. The terminal device 110 can be any type of mobile terminal, fixed terminal or portable terminal including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a television receiver, a radio broadcast receiver, an electronic book device, a game device, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some embodiments, the terminal device 110 can also support any type of interface for the user (such as "wearable" circuitry, etc.). The application 130 can be various types of computing systems / servers capable of providing computing capabilities, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, etc.

[0050] It should be understood that the structure and function of the various elements in the environment 100 are described for illustrative purposes only, without implying any limitation on the scope of the present disclosure.

[0051] Example Process

[0052] FIG. 2 A flowchart of a process 200 for message processing is shown in accordance with some embodiments of the present disclosure. The process 200 can be implemented by the server 130, the terminal device 110 or a combination of the server 130 and the terminal device 110 in the environment 100 (e.g., FIG. 1 For the convenience of description, the terminal device 110 is taken as an example below, and the process 200 is described with reference to the environment 100. FIG. 1 For the convenience of description, the terminal device 110 is taken as an example below, and the process 200 is described with reference to the environment 100.

[0053] As shown, at block 210, the terminal device 110 obtains recommendation information associated with the target object 140. In some embodiments, after generating the recommendation content, the server 130 can send the recommendation information associated with the recommendation content to the target object 140. Such recommendation information may, for example, include the recommendation content, or can be used to present the corresponding recommendation content by the terminal device 110.

[0054] At block 220, the terminal device 110 provides the recommendation content to the target object based on the recommendation information, wherein the recommendation content at least includes a first part corresponding to a first message classification, and the first part includes a first group of content items corresponding to the first message classification, wherein the first group of content items indicates a first group of conversations corresponding to the first message classification, and first description information about unread messages in the first group of conversations.

[0055] In some embodiments, the first message classification is determined based on a first degree of association of the unread messages in the first group of conversations with the current work of the target object, or the first message classification is determined based on time information of the unread messages in the first group of conversations.

[0056] The specific process of block 220 will be described below with reference to FIG. 3A FIG. 3A An example interface 300A is shown, which can be provided by the terminal device 110 according to some embodiments of the present disclosure.

[0057] As shown in FIG. 3, the terminal device 110 can provide the recommendation content 305, and the recommendation content 305 may, for example, include a plurality of parts corresponding to different message classifications. Further, each message classification can include a corresponding group of content items, for example, the first classification 310-1 can correspond to the content item 315-1, the second classification 310-2 can correspond to the content item 315-2, and the third classification 310-3 can correspond to the content item 315-3.

[0058] In some embodiments, such content items can be generated based on one or more unread messages in the corresponding conversation.

[0059] Specifically, the content item 315-1 may, for example, correspond to the conversation 320, the content item 315-2 may, for example, correspond to the conversation 330, and the content item 315-3 may, for example, correspond to the conversation 340.

[0060] ​Taking content item 315-1 as an example, content item 315-1 may, for example, indicate a conversation 320 corresponding to the first classification 310-1. Additionally, the terminal device 110 may also present the number of unread messages in the conversation 320. Additionally, content item 315-1 may also indicate description information 325 of the unread messages in the conversation 320.

[0061] In some embodiments, the description information 325 may, for example, be used to indicate the summary content of the unread messages in the conversation 320. Such summary content may, for example, include the subject of the unread messages, or the summary of the unread messages, etc. In some embodiments, the server 130 may, for example, utilize a language model to process the unread messages in the conversation 320 to generate the summary content about the unread messages.

[0062] In some embodiments, the description information 320 may, for example, also indicate the to-do content generated based on the unread messages in the conversation 320. As an example, the server 130 may, for example, also utilize a language model to process the unread messages in the conversation 320 to determine one or more to-do events of the target object 140.

[0063] It should be understood that such a language model can be implemented by any appropriate machine learning technique, and the present disclosure is not intended to be limited in this regard.

[0064] Further, the terminal device 110 may also provide one or more operation portals in association with the content item 315-1. For example, the terminal device 110 may provide a portal “clear unread” for quickly marking the unread messages in the conversation 320 as read.

[0065] As another example, the terminal device 110 may, for example, provide a portal “turn into task” for generating a corresponding reminder (e.g., a task) based on the to-do content in the content item 315-1.

[0066] As yet another example, the terminal device 110 may, for example, provide a portal associated with the conversation 320 to support the user to access the conversation window of the conversation 320. For example, the user may jump to the conversation window of the conversation 320 by clicking “X group”.

[0067] As introduced above, such recommended content 320 may also include content (e.g., content item 315-2 and content item 315-3) corresponding to other classifications (e.g., second classification 310-2 and third classification 310-3, etc.). Exemplarily, such different message classifications may include a first classification 310-1 (e.g., “high relevance”) corresponding to different work relevance, a second classification 310-2 (e.g., “some relevance”), and a third classification 310-3 (e.g., “low relevance”).

[0068] In some embodiments, the server 130 can utilize the historical interaction information of the target object 140 to determine the relevance of the message or the conversation to the current work of the target object 140.

[0069] The generation of the historical interaction information will be briefly introduced as follows. In some embodiments, when the target object 140 interacts with a business component, the business component can generate a log record and send the log record to a record module. Such a record module can run at a suitable electronic device, such as the server 130.

[0070] Further, the record module can generate a corresponding record entry based on the received log record and build a record library. In some embodiments, such a record entry can include a knowledge element (Knowledge) for describing the business object corresponding to the historical interaction event. In some embodiments, the record library can be maintained at a suitable electronic device, which can be stored at the terminal device 110 or at the server 130, for example.

[0071] In some embodiments, such a business object can include a business object generated by the target object 140 in the process of interacting with the business component, a business object edited by the target object 140, a business object referenced by the target object 140, a business object shared by the target object 140, etc. Taking the document component 115 as an example of a business component, the historical interaction event can include a creation event of a specific document in the document component by the target object 140. Accordingly, the business object corresponding to the document creation event is the specific document.

[0072] In some embodiments, the knowledge element can be a natural language description about the business object, which aims to abstract and / or compress the content of the business object. For example, taking the document object as an example of a business object, the knowledge element can be used to describe the theme, completion, audience, language, and expression style of the document object, etc.

[0073] It should be understood that different dimensions of information can be selected to generate the knowledge element for describing the business object according to the type of the business object. For example, taking the conversation as an example of a business object, the knowledge element can be used to describe the type of the conversation (e.g., whether it is a single chat), the summary of the conversation, etc.

[0074] Thus, by maintaining the knowledge element in the record entry, the embodiments of the present disclosure can describe or characterize the business object involved in the corresponding historical interaction event by a limited length of content.

[0075] In some embodiments, the record entry can also include a time element for indicating the occurrence time of the historical interaction event. For example, continuing with the example of creating a document as a historical interaction event, such a time element can indicate the creation time of the document, for example.

[0076] In yet some embodiments, the record entry can further include an action element for indicating an event type of the historical interaction event. Continuing with the example of creating a document as the historical interaction event, such an action element can indicate, for example, that the type of the historical interaction event is a "create" type.

[0077] In some embodiments, the record entry can further include a payload element for indexing a business object corresponding to the respective historical interaction event. With the document as the business object, the payload element can include, for example, a document number or a document identifier, etc. for indexing the document.

[0078] Thus, in some scenarios, the record module can generate a corresponding record entry after the target object 140 has interacted with the business component. Such a record entry can be represented as {time element, action element, knowledge element, payload element}, for example, to describe the historical interaction event from a plurality of preset dimensions. Such a record entry can also be referred to as historical interaction information corresponding to the interaction event.

[0079] Further, the server 130 can determine a set of work topics associated with the set of interaction events based on the historical interaction information.

[0080] In some embodiments, the server 130 can determine the set of topics, for example, by utilizing a target processing entity. Specifically, the server 130 can provide at least the knowledge element and the action element in the historical interaction information to the target processing entity for clustering processing of the historical interaction information by the target processing entity.

[0081] It should be appreciated that the target processing entity can be a processing entity based on appropriate information processing technology, and can implement one or more of text generation, image generation, summarization, encoding, translation, chatbot, etc. The target processing entity can also be in other any appropriate entity form. In some examples, the target processing entity can include, for example, a language model.

[0082] Illustratively, the target processing entity (e.g., a language model) can cluster a plurality of topics based on, for example, semantic analysis of the action elements and the knowledge elements in the historical interaction information.

[0083] In some embodiments, the at least one business component can include, for example, an office component used in work of the target object 140. Accordingly, the topics determined by the target processing entity can also be topics of work content (e.g., project name, etc.).

[0084] Further, the server 130 can obtain a topic set determined by the target processing entity based on the knowledge elements and the action elements. Illustratively, continuing with the example of the topic of the work content, such a topic set may, for example, include "X project", "Y project", and so on. In some embodiments, if some interaction events corresponding to the historical interaction information cannot be clustered into such topics, they may, for example, also be clustered into a preset category, e.g., "others".

[0085] In some embodiments, the server 130 may, for example, trigger an analysis of the historical interaction information periodically to determine the corresponding topic set. For example, the server 130 may, for example, trigger a full analysis of the historical interaction information every two weeks to determine the corresponding topic set with the target processing entity.

[0086] In some embodiments, the server 130 may, for example, also process newly obtained historical interaction information by merging clustering. For example, in a case where a topic set has been determined based on first historical interaction information within a first time period (e.g., before yesterday), the server 130 may, for example, also obtain second historical interaction information of the target object 140. Such second historical interaction information may, for example, be generated based on a second set of interaction events (also referred to as a second group of interaction events) within a second time period (e.g., yesterday).

[0087] Accordingly, the server 130 may, for example, determine a matching degree of the second group of interaction events to the topics in the topic set. Continuing with the example that the topic set includes "X project", "Y project", and "others", the server 130 may, for example, determine a matching degree of the second group of interaction events to "X project" or "Y project" based on the historical interaction information corresponding to the second group of interaction events.

[0088] Illustratively, the server 130 may, for example, determine the matching degree by providing the target processing entity with information such as the knowledge elements, the action elements, and so on of the historical interaction information corresponding to the second group of interaction events.

[0089] Further, the server 130 may, for example, determine an association between the second group of interaction events and the topic set based on the matching degree.

[0090] Specifically, in response to a matching degree of a first interaction event in the second group of interaction events to a target topic in the topic set reaching a threshold value, the server 130 may, for example, associate the first interaction event to the target topic. For example, if a certain event in the second group of interaction events matches "X project" to a threshold value, the historical interaction information corresponding to the interaction event may, for example, be marked as being associated with "X project".

[0091] In response to the matching degree of the second interaction event in the second set of interaction events to each of the topics in the set of topics except the preset topic being less than the threshold value, the second interaction event is associated to the preset topic. For example, if a certain event in the second set of interaction events matches both "X project" and "Y project" with a matching degree less than the threshold value, the historical interaction information corresponding to the interaction event can be marked as being associated to the preset topic "other".

[0092] In some embodiments, in response to the number of interaction events associated to the preset topic (e.g., "other") reaching a preset number, the server 130 can trigger a process of re-clustering. For example, the server 130 can determine at least one topic based on the historical interaction information corresponding to the plurality of interaction events associated to the preset topic. For example, if the number of events included in the topic "other" exceeds a threshold number, the server 130 may, for example, utilize a target processing entity to re-cluster the events in the topic to determine one or more new topics. Further, the server 130 can update the set of topics with the determined at least one topic.

[0093] Based on such a manner, embodiments of the present disclosure can cluster corresponding topics according to the historical interactions of the target object with the business components, thereby being able to facilitate the sorting of the historical interactions of the target object.

[0094] Further, the server 130 can determine the degree of association of each session to the current work of the target object based on the relevance between the unread messages in the session and the set of work topics. For example, the server 130 can utilize a language model to determine the relevance, e.g., the matching degree, between the unread messages in the session and each of the aggregated work topics.

[0095] In some embodiments, the server 130 may, for example, also provide a set of description items of the unread messages to the target model and obtain the relevance determined by the target model. As an example, the server 130 can provide the description items of the unread messages and each of the aggregated work topics to the target model, so as to determine the relevance between the description items and the target work topics by the target model.

[0096] In some embodiments, the description items of the unread messages may, for example, also include description items associated to the user associated with the unread messages. For example, such description items can indicate the relationship between the user sending the unread messages and the current user. Alternatively, such description items may, for example, also include at least other users mentioned in the unread messages, etc.

[0097] In some embodiments, the description items of the unread messages may, for example, also include attributes of the session in which the unread messages are located. For example, the attributes can include the session type of the session, e.g., a meeting group, a project group, etc.

[0098] Further, the server 130 can determine the degree of association between the conversation and the target object 140 based on the degree of association between each unread message in the conversation and the current work of the target object 140, and can determine the corresponding classification based on comparison of the degree of association with a preset range. For example, in a case where the degree of association is higher than a certain threshold, the conversation can be determined to have a higher relevance to the work.

[0099] Further reference is made to FIG. 3A For example, the description information 345 describes the reason why the conversation 340 is determined to have a low relevance.

[0100] In some embodiments, the recommended content 305 can further include a content item 315-4 corresponding to a fourth classification 310-4. The fourth classification 310-4 can indicate that unread messages in the corresponding conversations (e.g., the “A1 group”, the “A2 group”, and the “A3” group) are determined to be expired messages or invalid messages based on conversation attributes of the conversations. For example, the conversation “A1 group” can be a schedule conversation created based on a meeting schedule, and unread messages in the schedule conversation can be determined to be expired messages or invalid messages after a predetermined period of time from the end of the schedule.

[0101] As shown in FIG. 3, in some embodiments, the terminal device 110 can further present a subscription entry 350 in association with the recommended content 305. Further, based on selection of the subscription entry 350, the terminal device 110 can periodically provide the target object with recommended content corresponding to a corresponding period.

[0102] For example, in a case where the target object 140 subscribes to the recommended content (e.g., a daily unread message summary) through the subscription entry 350, the terminal device 110 can periodically (e.g., at a predetermined time in the morning every day) provide the target object 140 with an unread message summary of the previous day.

[0103] Further, in a case where the target object has subscribed to the recommended content, the terminal device 110 can present an unsubscription entry in association with the recommended content corresponding to a corresponding period. Accordingly, based on selection of the unsubscription entry, the terminal device 110 can stop providing the target object 140 with recommended content corresponding to a subsequent period.

[0104] Continuing with the example of unread message summaries, for a subsequently received unread message summary, the target object can trigger the terminal device 110 to stop providing such daily unread message summaries, e.g., by clicking on a corresponding unsubscribe entry.

[0105] In some embodiments, the recommended content 305 introduced above can be provided automatically by the terminal device 110, e.g. The digital assistant 120 can periodically provide recommended content for the target object 140 for curating unread messages of the target object 140.

[0106] In some embodiments, the recommended content 305 can also be provided in case the number of unread messages associated with the target object 140 reaches a threshold. Accordingly, in response to the number of unread messages associated with the target object 140 reaching the threshold, the server 120 can automatically send the recommended information associated with the target object 140 to the terminal device 110.

[0107] In some embodiments, the terminal device 110 can also provide the target object 140 with an acquisition entry for obtaining the recommended content 305, and can obtain the recommended information associated with the target object 140 from the server 120 based on the selection of the target object 140 for the acquisition entry, and present the corresponding recommended content 305.

[0108] As an example, as shown in FIG. 3B, the terminal device 110 can provide an acquisition entry 360-1 in association with a message tab 355 in a navigation bar of the conversation application. For example, the terminal device 110 can present the acquisition entry 360-1 based on a preset operation (e.g., a right-click operation) of the target object 140 for the message tab 355, e.g., when the target object 140 has unread messages, or when the number of unread messages of the target object 140 is greater than a threshold number. As an example, the terminal device 110 can also provide an entry 360-2 for marking all unread messages as read, e.g. FIG. 3B

[0109] As a further example, as shown in FIG. 3C, the navigation bar can have a greater width than the navigation bar shown in FIG. 3B, and accordingly, the terminal device 110 can present an acquisition entry 370 based on a preset operation (e.g., a hover operation) of the target object 140 for a message tab 365. Accordingly, in case of receiving a selection for the acquisition entry 370, the terminal device 110 can present the recommended content 305 as discussed above. FIG. 3C FIG. 3B

[0110] In some embodiments, the terminal device 110 can also provide an acquisition entry in a conversation of the target object 140 with the digital assistant 120, e.g. The target object 140 can trigger the presentation of the recommended content 305 by clicking on the acquisition entry, e.g.​​​

[0111] In some other embodiments, terminal device 110 may also receive input from target object 140 regarding organizing messages during a conversation between target object 140 and digital assistant 120, and may accordingly present corresponding recommended content 305.

[0112] In some other embodiments, terminal device 110 may also support target object 140 configuring a range of sessions to be processed. Specifically, terminal device 110 may determine a set of target sessions to be processed based on the configuration operations of target object 140. Accordingly, recommendation information generated based on unread messages in the set of target sessions is presented, and corresponding recommendation content 305 is displayed.

[0113] For example, target object 140 can specify one or more sessions to be tidied. Accordingly, the generated recommendation content 305 will only involve tidying up unread messages in the specified one or more sessions.

[0114] Therefore, embodiments of this disclosure can automatically organize unread messages based on their relevance to work, thereby improving the efficiency of message retrieval.

[0115] In some embodiments, different message categories in the recommended content can also be determined based on time information of unread messages in the corresponding session. FIG. 4 An example interface 400D according to some embodiments of the present disclosure is shown.

[0116] like FIG. 4 As shown, terminal device 110 can provide recommended content 405. In recommended content 405, terminal device 110 can provide different content items (e.g., content item 415-1, content item 415-2, content item 415-3, and content item 415-4) corresponding to different categories (e.g., category 410-1, category 410-2, and category 410-3).

[0117] Unlike categories 310-1 to 310-4 mentioned above, categories 410-1 to 410-3 can be determined based on the time information of unread messages (send time or receive time). For example, category 410-1 may correspond to a first time range (e.g., within 7 days); category 410-2 may correspond to a second time range (7 to 30 days); and category 410-3 may correspond to a third time range (e.g., more than 30 days).

[0118] Similar to the recommended content 305 discussed above, the content items corresponding to each category can indicate the corresponding conversation and the description information about the conversation. For example, the content item 415-1 can indicate the conversation 420 and the description information 425 of the unread messages in the conversation 420; the content item 415-2 can indicate the conversation 430 and the description information 435 of the unread messages in the conversation 430; the content item 415-3 can indicate the conversation 440 and the description information 445 of the unread messages in the conversation 440. As a further example, the content item 415-4 can also indicate a corresponding group of conversations.

[0119] Thus, embodiments of the present disclosure can automatically organize unread messages in a time range, thereby improving the efficiency of message acquisition.

[0120] FIG. 5 A flowchart of a process 500 for message processing according to some embodiments of the present disclosure is shown. The process 500 can be implemented by a suitable electronic device or a combination of electronic devices (e.g., the server 130, the terminal device 110, or a combination of the server 130 and the terminal device 110) in the system 100. For the convenience of description, the terminal device 110 is taken as an example, and the process 500 is described below with reference to the system 100. FIG. 1 FIG. 1

[0121] As shown in the figure, at block 510, the terminal device 110 provides at least one scene in the interaction window of the target object and the digital assistant, and the at least one scene includes a first scene; wherein the first scene is configured with corresponding configuration information to perform a task related to processing unread messages, and the configuration information includes at least one of the following: scene setting information and plug-in information, wherein the scene setting information is used to describe information related to processing unread messages, and the plug-in information indicates at least one plug-in used to perform the task related to processing unread messages.

[0122] In this document, in the context of the interaction of the user and the digital assistant, a "scene" refers to a collection of tasks of the same type, that is, one scene corresponds to multiple tasks of the same type. One or more scenes can be respectively configured with corresponding configuration information to perform tasks of the corresponding type. For the convenience of understanding, the scene applied in the interaction of the user and the digital assistant is briefly introduced.

[0123] ​​The configuration information of the scenario includes at least one of: scenario setting information, plugin information. The scenario setting information is used to describe information related to the corresponding scenario. The plugin information indicates at least one plugin used to perform a task under the corresponding scenario. As will be discussed below, the configuration information of the scenario may, for example, also include an indication of a selected model (here the model is invoked to determine a reply of the digital assistant to the user under the corresponding scenario), scenario guidance information (the scenario guidance information is presented to the user after the corresponding scenario is selected), at least one recommended question for the digital assistant (the at least one recommended question is presented to the user for selection after the corresponding scenario is selected), and the like. In some embodiments, the scenario setting information of the scenario and the configuration of the configuration information may, for example, be accomplished in a natural language manner, so that the scenario creator can conveniently constrain the output of the model and configure a diversified scenario.

[0124] The configuration information of the scenario includes at least one of: scenario setting information, plugin information. The scenario setting information is used to describe information related to the corresponding scenario. The scenario setting information of the scenario may, for example, include a description of a corresponding type of task, a style of a reply of the digital assistant under the scenario, a definition of a workflow to be performed under the corresponding scenario, a definition of a format of a reply of the digital assistant under the corresponding scenario, and the like. In some embodiments, the digital assistant will understand the user input with the help of the model and provide a reply to the user based on the output of the model. The model used by the digital assistant can run locally on the terminal device 110 or on a remote server. By using the scenario setting information to construct part of the prompt input of the model, the model can be guided to complete the task to be achieved under the corresponding scenario. In some embodiments, the model can be a machine learning model, a deep learning model, a learning model, a neural network, or the like. In some embodiments, the model can be based on a language model (LM). The language model can have the ability of question and answer by learning from a large amount of corpus. The model can also be based on other appropriate models.

[0125] The plugin information indicates at least one plugin used to perform a task under the corresponding scenario. Through the plugin information of the scenario, the plugin to be used under the corresponding scenario can be configured. In some embodiments, in the running of the plugin under the corresponding scenario, the plugin can also invoke the model to complete the corresponding task. In some embodiments, a certain plugin can also invoke an open interface provided by other business components (such as a document, a calendar, a meeting, and the like) to complete the corresponding task, such as modifying a document, creating a schedule, summarizing a meeting, and the like.

[0126] In some embodiments, the scenario configuration information may further include a scenario name, scenario description information, etc. In some embodiments, the terminal device 110 may provide a message card to the user in a session window, the message card presenting at least a portion of a set of scenarios. The terminal device 110 may present the scenario name and / or scenario description information of the corresponding scenario in the message card in association with the scenario. For example, the user may select a scenario that meets their needs based on the scenario name and / or scenario description information presented in the message card.

[0127] In some embodiments, the scenario configuration information may include, but is not limited to: the selected model (here, the model is invoked to determine the response to the user in the corresponding scenario), scenario guidance information (the scenario guidance information is presented to the user after the corresponding scenario is selected), at least one recommended question for the digital assistant (at least one recommended question is presented to the user for selection after the corresponding scenario is selected), any combination of one or more of the foregoing, etc. Scenario guidance information may, for example, be descriptive information about task instances that can be performed in the scenario. In some embodiments, the scenario setting information and configuration information can be configured, for example, through natural language, allowing scenario creators to easily constrain the model's output and configure diverse scenarios.

[0128] In some embodiments, the scene configuration information may also indicate at least one operational control associated with the scene. As will be described in detail below, at least one operational control associated with a scene may be presented to the user when the scene is selected for interaction, facilitating the user's interaction with the digital assistant within the corresponding scene. That is, during scene creation, the scene creator can configure at least one operational control associated with the corresponding scene. In some embodiments, the scene setting information and configuration information may be configured by the scene creator, for example, through natural language. This allows the scene creator to easily constrain the model's output and configure diverse scenes.

[0129] In some embodiments, if a scenario is selected for interaction between a first user and a first digital assistant, the interaction between the user and the digital assistant is performed in the session window based at least on the configuration information of the selected scenario. The scenario settings, plugin information, selected model, etc., of the selected scenario are used to guide the interaction within that scenario.

[0130] The following will be referenced FIG. 6A To describe the specific process of box 510. FIG. 6A An example interface 600A according to some embodiments of the present disclosure is shown. For example... FIG. 6AAs shown, the terminal device 110 provides content 605 in the interaction window of the target object 140 and the digital assistant 120, which can include at least one scenario, e.g., scenario 610 and scenario 615. The scenario 610 can correspond to a first scenario for "unread message summary", for example, which can be configured with corresponding configuration information to perform the task related to processing unread messages. The scenario 615 can correspond to a second scenario for "content understanding", for example. The user can also select other more scenarios through the control 620, for example.

[0131] With reference back to FIG. 5 At block 520, in response to the preset operation of the target object on the first scenario, the terminal device 110 performs the interaction of the target object and the digital assistant based at least on the configuration information of the first scenario.

[0132] As an example, in the case where the scenario 610 is selected, the terminal device 110 can present an interface 600B as shown. FIG. 6B In the interface 600B, the digital assistant 120 can provide content 640, which can include a set of recommended questions 645, 650 and 655. Such different recommended questions can correspond to different interaction requests.

[0133] For example, the recommended question 645 can be used to trigger the acquisition of the summary content for all unread messages. The recommended question 650 can trigger the acquisition of the summary content for unread messages in a specified session. The recommended question 655 can trigger the subscription of the summary content for unread messages.

[0134] As an example, in the case where the user selects the recommended question 645, the corresponding input content 660 can be sent to the digital assistant. Further, as shown, FIG. 6C the terminal device 110 can provide recommended content 665 generated for all unread messages.

[0135] The specific content and generation process of the recommended content 665 can be referred to the content described above with reference to FIGS. 2-4 and will not be repeated here.

[0136] Based on the above discussed process, the embodiments of the present disclosure can provide the user with a scenario for summarizing unread messages, thereby improving the efficiency of the user in summarizing unread messages.

[0137] Example Devices and Apparatus

[0138] FIG. 7A A schematic structural block diagram of an apparatus 700A for message processing according to certain embodiments of the present disclosure is shown. The apparatus 700A can be implemented as or included in a terminal device, a server, or the like. FIG. 1the server 130, the terminal device 110, or a combination of the server 130 and the terminal device 110. The various modules / components in the apparatus 700A can be implemented by hardware, software, firmware, or any combination thereof.

[0139] As shown, the apparatus 700A includes an information obtaining module 710 configured to obtain recommendation information associated with a target object, and a content providing module 720 configured to provide, based on the recommendation information, recommendation content to the target object, where the recommendation content includes at least a first part corresponding to a first message classification, the first part including a first set of content items corresponding to the first message classification, where the first set of content items indicates a first set of conversations corresponding to the first message classification, and first description information about unread messages in the first set of conversations, and the first message classification is determined based on a first degree of association between the unread messages in the first set of conversations and a current work of the target object, or the first message classification is determined based on time information of the unread messages in the first set of conversations.

[0140] In some embodiments, the recommendation content further includes a second part corresponding to a second message classification, the second part including a second set of content items corresponding to the second message classification, and the second set of content items is generated based on a second set of conversations associated with the second message classification.

[0141] In some embodiments, the second set of conversations corresponding to the second message classification has a second degree of association with the current work of the target object that is lower than a threshold degree, and the second set of content items includes second description information about the second degree of association between the second set of conversations and the target object being lower than the threshold degree.

[0142] In some embodiments, the second message classification indicates that unread messages in the second set of conversations are determined to be expired messages or invalid messages based on conversation attributes of the second set of conversations.

[0143] In some embodiments, the first degree of association is determined based on the following process: obtaining historical interaction information of the target object, the historical interaction information being generated based on a set of interaction events between the target object and at least one business component; determining, based on the historical interaction information, a set of work topics associated with the set of interaction events; and determining, based on a relevance between the unread messages in the first set of conversations and the set of work topics, the first degree of association between the first set of conversations and the current work of the target object.

[0144] In some embodiments, the first degree of association is further determined based on the following process: providing a set of description items about the unread messages to a target model to obtain a relevance determined by the target model.

[0145] In some embodiments, the description information indicates at least one of: summarized content about a set of unread messages in the respective session of the first group of sessions; to-do content generated based on the set of unread messages.

[0146] In some embodiments, the apparatus 700A further includes an entry providing module configured to: provide a first entry for marking the set of unread messages in the respective session as read; provide a second entry for generating a reminder corresponding to the to-do content; or provide a third entry for displaying a session window of the respective session.

[0147] In some embodiments, the apparatus 700A further includes a subscription module configured to: present a subscription entry in association with the recommended content; and based on a selection for the subscription entry, periodically provide the recommended content corresponding to the respective time period to the target object.

[0148] In some embodiments, the apparatus 700A further includes an unsubscription module configured to: present an unsubscription entry in association with the recommended content corresponding to the respective time period; and based on a selection for the unsubscription entry, cease providing the recommended content corresponding to a subsequent time period to the target object.

[0149] In some embodiments, the information obtaining module 710 is further configured to: in response to a number of unread messages associated with the target object reaching a threshold value, obtain the recommended information associated with the target object.

[0150] In some embodiments, the information obtaining module 710 is further configured to: provide an obtaining entry for obtaining the recommended content; and based on a preset operation for the obtaining entry, obtain the recommended information associated with the target object.

[0151] In some embodiments, the information obtaining module 710 is further configured to: provide the obtaining entry in association with a message tab in a navigation bar of the session application; or provide the obtaining entry in a session of the target object with the digital assistant.

[0152] In some embodiments, the information obtaining module 710 is further configured to: based on a configuration operation of the target object, determine a set of target sessions to be processed; and obtain the recommended information associated with the target object, wherein the recommended information is generated based on unread messages in the set of target sessions.

[0153] FIG. 7B A schematic structural block diagram of an apparatus 700B for message processing according to certain embodiments of the present disclosure is shown. The apparatus 700B can be implemented as or included in a FIG. 1The server 130, the terminal device 110, or a combination of the server 130 and the terminal device 110. Each module / component in the apparatus 700B can be implemented by hardware, software, firmware, or any combination thereof.

[0154] As shown, the apparatus 700B includes a scenario providing module 730 configured to provide at least one scenario in an interaction window of a target object and a digital assistant, the at least one scenario including a first scenario; wherein the first scenario is configured with corresponding configuration information to perform a task related to processing an unread message, the configuration information including at least one of: scenario setting information describing information related to processing the unread message, and plug-in information indicating at least one plug-in used to perform the task related to processing the unread message; and an interaction module 740 configured to perform an interaction between the target object and the digital assistant based at least on the configuration information of the first scenario in response to a preset operation of the target object on the first scenario.

[0155] In some embodiments, the configuration information further includes at least one of: an indication of a selected model invoked to determine a reply to the target object in the first scenario; scenario guidance information presented to the target object after the first scenario is selected; or at least one recommended question for the digital assistant presented to the target object for selection after the first scenario is selected.

[0156] In some embodiments, the scenario setting information is used to construct a prompt word input to provide to a model used in the first scenario, the reply to the target object being based on an output of the model.

[0157] In some embodiments, the interaction module 740 is further configured to provide recommended content by the digital assistant, wherein the recommended content includes at least a first part corresponding to a first message classification, the first part including a first set of content items corresponding to the first message classification, wherein the first set of content items indicates: a first set of conversations corresponding to the first message classification, and first description information about unread messages in the first set of conversations.

[0158] In some embodiments, the first message classification is determined based on a first degree of association between the unread messages in the first set of conversations and a current work of the target object; or the first message classification is determined based on time information of the unread messages in the first set of conversations.

[0159] The electronic device 800 typically includes a plurality of computer storage media. Such media can be removable, non-removable, or a combination thereof. Storage memory 820 can be volatile (such as registers, cache, or random access memory (RAM)), non-volatile (such as read-only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory), or some combination thereof. Storage devices 830 can be removable or non-removable, and can include machine- readable media, such as flash drives, disks, or any other media, which can be capable of storing information and / or data and which can be accessed within the electronic device 800.

[0160] The electronic device 800 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 8 FIG. 8, a disk drive for reading from or writing to a removable, non- volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable, non-volatile optical disk (e.g., a CD-ROM) can be provided. In such instances, each drive can be connected to the bus (not shown) by one or more data media interfaces. The storage memory 820 can include a computer program product 825 having one or more program modules configured to carry out the various methods or actions of the various embodiments of the present disclosure.

[0161] The communication unit 840 enables communications with other electronic devices over a communication medium. Additionally, the functionality of the components of the electronic device 800 can be implemented in a single computing cluster or a plurality of computer machines capable of communicating over a communication connection. As such, the electronic device 800 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network nodes in the networking environment.

[0162] The input device 850 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. The output device 860 can be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 800 can also communicate with one or more external devices (not shown) such as a storage device, a display device, etc. through the communication unit 840, as needed, one or more devices that enable a user to interact with the electronic device 800, or any devices (e.g., a network card, a modem, etc.) that enable the electronic device 800 to communicate with one or more other electronic devices. Such communication can be carried out via an input / output (I / O) interface (not shown).

[0163] According to an example implementation of the present disclosure, a computer readable storage medium is provided having computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to implement the method described above. According to an example implementation of the present disclosure, a computer program product is also provided that is tangibly stored on a non-transitory computer readable medium and includes computer executable instructions, where the computer executable instructions are executed by a processor to implement the method described above.

[0164] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0165] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0166] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0167] The computer program product of the present disclosure can have a signal including said computer program. This signal can be electronic, electromagnetic, optical, or any other suitable type of signal. Such a signal can be provided through a communication connection, such as electrical wiring, optical fiber, wireless interface, etc. Examples of computer program products include computer program implemented on a personal computer, server, or other networked device. A non-transitory computer readable medium, such as a floppy disk, CD-ROM, DVD-ROM, Blu-ray Disc, hard disk drive, or any other suitable non-transitory computer readable medium can store the computer program product.

[0168] Having described several implementations of the present disclosure, it is to be appreciated various alterations, modifications, and improvements will readily occur to those skilled in the art. Such alterations, modifications, and improvements are intended to be part of this disclosure. Accordingly, the foregoing description is by way of example only and is not intended to be limiting. The implementation described herein is implementations of the present disclosure. Other implementations of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the present disclosure. Therefore, this disclosure is intended to cover all such modifications and variations as fall within the scope of the implementations. It is intended that the specification and depicted embodiments are to be considered exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A message processing method, comprising: Obtain recommendation information associated with the target object; as well as Based on the recommendation information, recommended content is provided to the target object, wherein the recommended content includes at least a first part corresponding to a first message category, the first part including a first group of content items corresponding to the first message category, wherein the first group of content items indicates: a first group of conversations corresponding to the first message category, and first descriptive information about unread messages in the first group of conversations. The first message classification is determined based on the degree of correlation between unread messages in the first group of sessions and the current work of the target object. The first degree of association is determined based on the following process: Obtain historical interaction information of the target object, which is generated based on a set of interaction events between the target object and at least one business component; Based on the historical interaction information, determine the set of work topics associated with the set of interaction events; and Based on the correlation between the unread messages in the first group of sessions and the set of work topics, the first degree of association between the first group of sessions and the current work of the target object is determined.

2. The method according to claim 1, wherein the recommended content further includes a second part corresponding to the second message category, the second part including a second group of content items corresponding to the second message category, the second group of content items being generated based on a second group of sessions associated with the second message category.

3. The method of claim 2, wherein the second set of content items and the second set of sessions corresponding to the second message category have a second degree of association with the current work of the target object that is less than a threshold, and the second set of content items includes second descriptive information regarding the second degree of association between the second set of sessions and the target object that is less than the threshold.

4. The method of claim 2, wherein the second message classification indicates that unread messages in the second group of sessions are determined to be expired or invalid messages based on the session attributes of the second group of sessions.

5. The method of claim 1, wherein the first degree of association is further determined based on the following process: A set of descriptive terms about the unread messages is provided to the target model to obtain the relevance determined by the target model.

6. The method of claim 1, wherein the descriptive information indicates at least one of the following: An overview of a set of unread messages in the corresponding session of the first group of sessions; The to-do list is generated based on the set of unread messages.

7. The method according to claim 6, further comprising: A first entry point is provided, which is used to mark the set of unread messages in the corresponding session as read; A second entry point is provided, which is used to generate reminders corresponding to the to-do items; or A third entry point is provided, which is used to display the session window of the corresponding session.

8. The method according to claim 1, further comprising: A subscription entry point is displayed in conjunction with the recommended content; as well as Based on the selection of the subscription entry point, recommended content corresponding to the corresponding time period is periodically provided to the target audience.

9. The method of claim 8, further comprising: An unsubscribe option is presented in conjunction with the recommended content corresponding to the relevant time period; as well as Based on the selection of the unsubscribe entry, the provision of recommended content corresponding to subsequent time periods to the target audience will cease.

10. The method of claim 1, wherein obtaining recommendation information associated with the target object comprises: In response to the number of unread messages associated with the target object reaching a threshold, recommendation information associated with the target object is obtained.

11. The method of claim 1, wherein obtaining recommendation information associated with the target object comprises: Provide an access point for obtaining the recommended content; as well as Based on the preset operation for the acquisition entry, the recommendation information associated with the target object is acquired.

12. The method of claim 11, wherein providing an access point for obtaining the recommended content includes: The message tab in the navigation bar of the session application provides the access point; or The access point is provided during the session between the target object and the digital assistant.

13. The method of claim 1, wherein obtaining recommendation information associated with the target object comprises: Based on the configuration operations of the target object, a set of target sessions to be processed is determined; as well as Obtain the recommendation information associated with the target object, wherein the recommendation information is generated based on unread messages in the set of target sessions.

14. A message processing method, comprising: The interaction window between the target object and the digital assistant provides at least one scenario, including a first scenario; wherein the first scenario is configured with corresponding configuration information to perform tasks related to handling unread messages, the configuration information including at least one of the following: scenario setting information and plugin information, wherein the scenario setting information describes information related to unread message handling, and the plugin information indicates at least one plugin for performing tasks related to unread message handling; and In response to the target object's preset operation on the first scenario, the digital assistant provides recommended content based at least on the configuration information of the first scenario. The recommended content includes at least a first part corresponding to the first message category. The first part includes a first group of content items corresponding to the first message category. The first group of content items indicates: a first group of conversations corresponding to the first message category, and first descriptive information about unread messages in the first group of conversations.

15. The method of claim 14, wherein the configuration information further comprises at least one of the following: The selected model is invoked to determine the response to the target object in a first scenario; Scene guidance information is presented to the target object after the first scene is selected. or In response to at least one recommended question from the digital assistant, after a first scenario is selected, the at least one recommended question is presented to the target object for selection.

16. The method of claim 14, wherein the scene setting information is used to construct a prompt word input to be provided to a model used in a first scene, and the response to the target object is based on the output of the model.

17. The method of claim 14, wherein: The first message classification is determined based on the degree of correlation between unread messages in the first group of sessions and the current work of the target object; or The first message classification is determined based on the time information of unread messages in the first group of sessions.

18. An apparatus for message processing, comprising: The information acquisition module is configured to acquire recommendation information associated with the target object; as well as A content providing module is configured to provide recommended content to the target object based on the recommendation information, wherein the recommended content includes at least a first part corresponding to a first message category, the first part including a first group of content items corresponding to the first message category, wherein the first group of content items indicates: a first group of sessions corresponding to the first message category, and first descriptive information about unread messages in the first group of sessions. The first message classification is determined based on the degree of correlation between unread messages in the first group of sessions and the current work of the target object. The first degree of association is determined based on the following process: Obtain historical interaction information of the target object, which is generated based on a set of interaction events between the target object and at least one business component; Based on the historical interaction information, determine the set of work topics associated with the set of interaction events; and Based on the correlation between the unread messages in the first group of sessions and the set of work topics, the first degree of association between the first group of sessions and the current work of the target object is determined.

19. An apparatus for message processing, comprising: A scene providing module is configured to provide at least one scene in the interaction window between the target object and the digital assistant, the at least one scene including a first scene; wherein the first scene is configured with corresponding configuration information to perform tasks related to handling unread messages, the configuration information including at least one of the following: scene setting information and plugin information, wherein the scene setting information is used to describe information related to unread message handling, and the plugin information indicates at least one plugin for performing tasks related to unread message handling; and An interaction module is configured to respond to a preset operation of the target object on the first scenario, and to provide recommended content by the digital assistant based at least on the configuration information of the first scenario. The recommended content includes at least a first part corresponding to a first message category, the first part including a first group of content items corresponding to the first message category, wherein the first group of content items indicates: a first group of conversations corresponding to the first message category, and a first descriptive information about unread messages in the first group of conversations.

20. 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 13 or 14 to 17 when executed by the at least one processing unit.

21. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 13 or 14 to 17.

Images