Detailed Description
It will be appreciated that, before using the technical solutions disclosed in the embodiments of the present disclosure, the relevant users should be informed and authorized by appropriate means of the types, usage ranges, usage scenarios, etc. of the information involved in the present disclosure according to the relevant laws and regulations. The relevant users may include any type of rights body, such as individuals, businesses, communities, among others.
For example, in response to receiving an active request from a user, a prompt is sent to the relevant user to explicitly prompt the relevant user that the operation it is requesting to perform will require information to be retrieved and used by the relevant user. Therefore, the related user can autonomously select whether to provide information for software or hardware such as electronic equipment, application programs, servers or storage media for executing the operation of the technical scheme of the disclosure according to the prompt information.
As an alternative but non-limiting implementation, in response to receiving an active request from a relevant user, the manner in which the prompt information is sent to the relevant user may be, for example, a pop-up window, in which the prompt information may be presented in a text manner. In addition, a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device may also be carried in the pop-up window.
It will be appreciated that the above-described notification and user authorization process is merely illustrative and not limiting of the implementations of the present disclosure, and that other ways of satisfying relevant legal regulations may be applied to the implementations of the present disclosure.
It will be appreciated that, when the present technical solution is adopted, the data involved (including but not limited to the data itself, the acquisition, use, storage, and transmission of the data) should comply with the corresponding legal regulations and the requirements of the relevant regulations.
The term "responsive to" as used herein means a state in which a corresponding event occurs or a condition is satisfied. It will be appreciated that the execution timing of a subsequent action that is executed in response to the event or condition is not necessarily strongly correlated with the time at which the event occurs or the condition is established. For example, in some cases, the follow-up actions may be performed immediately upon occurrence of an event or establishment of a condition; in other cases, the subsequent action may be performed after a period of time has elapsed after the event occurred or the condition was established.
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been illustrated in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather, these embodiments are provided so that this disclosure will be more thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be noted that any section/subsection headings provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment may be included under any section/subsection. Furthermore, the embodiments described in any section/subsection may be combined in any manner with any other embodiment described in the same section/subsection and/or in a different section/subsection.
In describing embodiments of the present disclosure, the term "comprising" and its like should be taken to be open-ended, i.e., including, but not limited to. The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions are also possible below. The terms "first," "second," and the like, may refer to different or the same object. Other explicit and implicit definitions are also possible below.
As used herein, the term "model" may learn the association between the respective inputs and outputs from training data so that, for a given input, a corresponding output may be generated after training is completed. The generation and use of the model can be based on technologies allowed by laws and regulations such as machine learning, and the available technologies are short for short. Illustratively, deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs through the use of multiple layers of processing units. The "model" may also be referred to herein as a "machine learning model," "machine learning network," or "network," and these terms are used interchangeably herein. A model may in turn comprise different types of processing units or networks.
As mentioned briefly above, in the internet platform, people can obtain various types of messages, which results in a large number of unread messages that people may need to process. Thus, how to increase the processing efficiency for unread messages has become a focus of attention.
Embodiments of the present disclosure provide a scheme for message processing. Specifically, recommendation information associated with the target object may be obtained. Further, recommended content may be provided to the target object based on the recommendation information, wherein the recommended content includes at least a first portion corresponding to the first message classification, the first portion 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 descriptive information about unread messages in the first set of conversations, wherein the first message classification is determined based on a first degree of association of the unread messages in the first set of conversations with 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. Therefore, the embodiment of the disclosure can sort the unread messages according to the correlation degree or time information of the work, thereby improving the efficiency of message acquisition.
Example embodiments of the present disclosure are described below with reference to the accompanying drawings.
Example Environment
FIG. 1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure may be implemented. In this example environment 100, a digital assistant 120 and an application 125 are installed in a terminal device 110. The target object 140 may interact with the digital assistant 120 and the application 125 via the terminal device 110 and/or an attachment device of the terminal device 110.
In some embodiments, the digital assistant 120 and the application 125 may be downloaded and installed at the terminal device 110. In some embodiments, the digital assistant 120 and the application 125 may also be accessed by other means, such as by web page access, etc. In the environment 100 of fig. 1, in response to the application 125 being launched, the terminal device 110 may present an interface 150 of the digital assistant 120 and the application 125.
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 video conferencing applications, mail applications, task applications, calendar applications, target and key results (OKR) applications, and so forth. Although a single application is shown in fig. 1, a plurality of applications may be installed on the terminal device 110 in practice. In some embodiments, the application 125 may include a multi-functional collaboration platform, such as an office collaboration platform (also referred to as an office suite) capable of providing integration of various types of business components, such as chat components, document components, calendar components, audio-visual conferencing components, etc., to facilitate activities such as offices, communications, etc. In the multifunctional collaboration platform, people can start different business components as required to complete corresponding information processing, sharing, communication and the like.
The application 125 may provide a content entity 126. Content entity 126 may be a content instance created on application 125 by target object 140 or other user. For example, depending on the type of application 125, the content entity 126 may be a document (e.g., word document, pdf document, presentation, form document, etc.), mail, message (e.g., conversation message on an instant messaging application), calendar, task, audio, video, image, etc.
In some embodiments, the digital assistant 120 may be provided by a separate application or may be integrated into some application 120 capable of providing the content entity. The application used to provide the client interface of the digital assistant may correspond to a single-function application or a multi-function collaboration platform, such as an office suite or other collaboration platform capable of integrating multiple components. In some embodiments, the digital assistant 120 supports the use of a plug-in. Each plug-in is capable of providing one or more functions of an application or business component. Such inserts include, but are not limited to, one or more of the following: search plug-ins, contact plug-ins, message plug-ins, document plug-ins, form plug-ins, mail plug-ins, calendar plug-ins, task plug-ins, and the like.
The digital assistant 120 is a user's intelligent assistant with intelligent dialog and information processing capabilities. In an embodiment of the present disclosure, the digital assistant 120 is used to interact with the target object 140 to assist the target object 140 in using a terminal device or application. An interactive window with the digital assistant 120 may be presented in the client interface. In the interactive window, the target object 140 is able to speak with the digital assistant 120 by entering natural language to instruct the digital assistant to assist in accomplishing various tasks, including operations on the content entity 126.
In some embodiments, the digital assistant 120 may be included as a contact for the target object 140, in a contact list for the current target object 140 in an office suite, or in an information stream of a chat component. In some embodiments, the target object 140 has a correspondence 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 may uniquely correspond to a first user, the second digital assistant may uniquely correspond to a second user, and so on. That is, the first digital assistant of the first user may be specific or dedicated to the first user. For example, in the process of the first digital assistant providing assistance or services to the first user, the first digital assistant may utilize its historical interaction information with the first user, the first user-authorized data it has access to, its current interaction context with the first user, and so on. If the first user is an individual or a person, the first digital assistant may be considered a personal digital assistant. It will be appreciated that in the disclosed embodiment the first digital assistant is based on the first user's authorization to access the granted rights data. It should be appreciated that the "unique correspondence" or similar expressions in this disclosure are not intended to limit that the first digital assistant will be updated accordingly based on the interaction process between the first user and the first digital assistant. Of course, depending on the actual application requirements, the digital assistant 120 need not be specific to the current target object 140, but may be a general purpose digital assistant.
In some embodiments, multiple modes of interaction of the target object 140 with the digital assistant 120 may be provided and flexible switching between the multiple modes of interaction may be possible. In the event that a certain interaction pattern is triggered, a corresponding interaction zone is presented to facilitate interaction of the target object 140 with the digital assistant 120. The interaction modes of the target object 140 and the digital assistant 120 in different interaction modes are different, so that the interaction modes can be flexibly adapted to the interaction requirements in different application scenes.
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 with the digital assistant 120 and/or a data range specific to the target object 140. In some embodiments, historical interaction information for the target object 140 interacting with the digital assistant 120 in multiple interaction modes, respectively, may each be stored in association with the target object 140. In this way, in one of the plurality of interaction modes (either or a designated one), the digital assistant 120 may provide services to the target object 140 based on the historical interaction information stored in association with the target object 140.
The digital assistant 120 may be invoked or awakened in an appropriate manner (e.g., a shortcut, button, or voice) to present an interactive window with the target object 140. By selecting the digital assistant 1201, an interaction window with the digital assistant 120 may be opened. The interactive window may include interface elements for information interaction, such as input boxes, message lists, message bubbles, and the like. In other embodiments, the digital assistant 120 may be invoked by entry controls or menus provided in the page, or by entering preset instructions.
The interactive window of the digital assistant 120 with the target object 140 may include a conversation window, such as in an instant messaging module of an instant messaging application or a target application. In some embodiments, the interactive window of the digital assistant 120 with the target object 140 may include a floating window corresponding to the digital assistant.
In some embodiments, the digital assistant 120 may support an interactive mode of the conversation window, also referred to as a conversation mode. In this interaction mode, a conversation window of the target object 140 with the digital assistant 120 is presented, in which the target object 140 interacts with the digital assistant 120 through conversation messages. In the conversation mode, the digital assistant 120 can perform tasks based on conversation messages in the conversation window.
In some embodiments, the session mode of the target object 140 with the digital assistant 120 may be invoked or awakened in an appropriate manner (e.g., a shortcut, button, or voice) to present a session window. By selecting the digital assistant 120, a session window with the digital assistant 120 may be opened. The session window may include interface elements for information interaction, such as input boxes, message lists, message bubbles, and the like.
In some embodiments, the digital assistant 120 may support a floating window (or floating window) interaction mode, 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 may issue an instruction to the digital assistant 120 based on the operation panel. In some embodiments, the operation panel may include at least one candidate shortcut. Alternatively or additionally, the operation panel may comprise input controls for receiving instructions. In the floating window mode, the digital assistant 120 may perform tasks according to instructions issued by the target object 140 through the operation panel.
In some embodiments, the floating window mode of the target object 140 and the digital assistant 120 may also be invoked or awakened in an appropriate manner (e.g., a shortcut key, button, or voice) to present a corresponding operation panel. In some embodiments, wake-up of digital assistant 120 may be supported in a particular application, such as in a document business component, to provide floating window mode interaction. 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 may be presented in the application interface. In response to detecting a triggering operation for the portal control, it may be determined that the floating window mode is triggered and an operation panel corresponding to the digital assistant 120 is presented in the target interface area.
In some embodiments described below, for ease of discussion, the user's interaction window with the digital assistant is primarily described as a conversation window.
In some embodiments, terminal device 110 communicates with server 130 to enable provisioning of services for digital assistant 120 and application 125. The terminal device 110 may be any type of mobile terminal, fixed terminal, or portable terminal, including a mobile handset, desktop computer, laptop computer, notebook computer, netbook computer, tablet computer, media computer, multimedia tablet, personal Communication System (PCS) device, personal navigation device, personal Digital Assistant (PDA), audio/video player, digital camera/camcorder, television receiver, radio broadcast receiver, electronic book device, game device, or any combination of the preceding, including accessories and peripherals for these devices, or any combination thereof. In some embodiments, terminal device 110 is also capable of supporting any type of interface to the user (such as "wearable" circuitry, etc.). The applications 130 may be various types of computing systems/servers capable of providing computing capabilities, including, but not limited to, mainframes, edge computing nodes, computing devices in a cloud environment, and so forth.
It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and are not meant to suggest any limitation as to the scope of the disclosure.
Example procedure
Fig. 2 illustrates a flow chart of a process 200 for message processing according to some embodiments of the present disclosure. Process 200 may be implemented by an appropriate electronic device or combination of electronic devices (e.g., server 130, terminal device 110, or a combination of server 130 and terminal device 110 in fig. 1). For convenience of description, the process 200 is described below with reference to fig. 1, taking the terminal device 110 as an example.
As shown, at block 210, the terminal device 110 obtains recommendation information associated with the target object 140. In some embodiments, after generating the recommended content, the server 130 may send recommendation information associated with the recommended content to the target object 140. Such recommendation information may, for example, comprise the recommendation content or be available for presentation of the corresponding recommendation content by the terminal device 110.
At block 220, the terminal device 110 provides recommended content to the target object based on the recommendation information, wherein the recommended content includes at least a first portion corresponding to the first message classification, the first portion 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 descriptive information about unread messages in the first set of conversations.
In some embodiments, the first message classification is determined based on a first degree of association of the unread messages in the first set of sessions 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 set of sessions.
The specific process of block 220 will be described below with reference to fig. 3A. Fig. 3A illustrates an example interface 300A, which interface 300 may be provided by, for example, terminal device 110, in accordance with some embodiments of the present disclosure.
As shown in fig. 3, the terminal device 110 may provide the recommended content 305, and the recommended content 305 may include, for example, a plurality of portions corresponding to different message classifications. Further, each message category may include a corresponding set of content items, e.g., a first category 310-1 may correspond to content item 315-1, a second category 310-2 may correspond to content item 315-2, and a third category 310-3 may correspond to content item 315-3.
In some embodiments, such content items may be generated based on one or more unread messages in the corresponding session.
In particular, content item 315-1 may correspond to session 320, content item 315-2 may correspond to session 330, and content item 315-3 may correspond to session 340, for example.
Taking content item 315-1 as an example, content item 315-1 may, for example, indicate a session 320 corresponding to a first category 310-1. Additionally, terminal device 110 may also present the number of unread messages in session 320. Additionally, content item 315-1 may also indicate description information 325 of unread messages in session 320.
In some embodiments, descriptive information 325 may be used, for example, to indicate summary content of unread messages in session 320. Such summary content may include, for example, the subject matter of the unread message, or a summary of the unread message, etc. In some embodiments, server 130 may process the unread messages in session 320, for example, using a language model, to generate summary content about the unread messages.
In some embodiments, the descriptive information 320 may also indicate, for example, to-Do content generated based on unread messages in the session 320. As an example, server 130 may also process unread messages in session 320, for example, using a language model, to determine one or more to-Do events for target object 140.
It should be appreciated that such a language model may be implemented by any suitable machine learning technique, and this disclosure is not intended to be limiting.
Further, terminal device 110 can also provide one or more operation portals in association with content item 315-1. For example, terminal device 110 may provide an entry "clear unread" for quickly marking unread messages in session 320 as read.
As another example, the terminal device 110 may provide, for example, an entry "turn to task" to generate a corresponding reminder (e.g., task) based on the to-do content in the content item 315-1.
As yet another example, terminal device 110 provides, for example, a portal associated with session 320 to support user access to a session window of session 320. For example, the user may jump to the session window of session 320 by clicking on "X group".
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.). By way of example, such different message classifications may include a first classification 310-1 (e.g., "higher-relevance"), a second classification 310-2 (e.g., "certain-relevance"), and a third classification 310-3 (e.g., "not higher-relevance"), which correspond to different work correlations.
In some embodiments, the server 130 may utilize the historical interaction information of the target object 140 to determine how relevant the message or session is to the current operation of the target object 140.
The generation process of the history interaction information will be briefly described below. In some embodiments, the business component may generate a log record and send the log record to the logging module when the target object 140 interacts with the business component. Such a recording module may run at an appropriate electronic device such as server 130.
Further, the logging module may generate corresponding logging entries based on the received log records and build a logging library. In some embodiments, such record entries may include a Knowledge element (knowledges) for describing business objects corresponding to historical interaction events. In some embodiments, the record repository may be maintained at a suitable electronic device process, which may be stored at terminal device 110, or at server 130, for example.
In some embodiments, such business objects may include business objects generated by the target object 140 in interacting with business components, edited business objects, referenced business objects, shared business objects, and the like. Taking business component 115 as a document component as an example, the historical interaction events may include creation events of a particular document in the document component by target object 140. Accordingly, the business object corresponding to the document creation event is the specific document.
In some embodiments, the knowledge element may be a natural language description about the business object that is intended to abstract and/or compress the content of the business object. Illustratively, the knowledge element may be used to describe the subject matter, completion, audience, language, expression style, etc. of the document object as an example of a business object.
It should be appreciated that the information of different dimensions may be selected to generate knowledge elements describing the business object according to the type of the business object. For example, with a session as an example of a business object, knowledge elements may be used, for example, to describe the type of session (e.g., whether it is a single chat), an overview of the session, and so on.
Thus, by maintaining knowledge elements in record entries, embodiments of the present disclosure may describe or characterize business objects involved in corresponding historical interaction events through a limited content length.
In some embodiments, the record entry may also include a time element for indicating the time of occurrence of the historical interaction event. For example, continuing to create a document as an example of a historical interaction event, such a time element may indicate, for example, a creation time of the document.
In still other embodiments, the record entry may also include an action element for indicating an event type of the historical interaction event. Continuing with the example of creating a document as a historical interaction event, such an action element may indicate that the type of historical interaction event is a "create" type, for example.
In some embodiments, the record entry may also include a load element for indexing the business object corresponding to the respective historical interaction event. Taking a document as an example of a business object, the payload element may include, for example, a document number or document identifier or the like for indexing the document.
Thus, in some scenarios, after the target object 140 interacts with the business component, the record module may generate a corresponding record entry. Such a record entry may be expressed, for example, as { time element, action element, knowledge element, load element }, to describe the historical interaction event from a preset plurality of dimensions. Such record entries may also be referred to as historical interaction information corresponding to interaction events.
Further, server 130 may associate a set of work topics with the set of interaction events based on the historical interaction information.
In some embodiments, server 130 may utilize, for example, a target processing entity to determine a set of topics. In particular, the server 130 may provide at least knowledge elements and action elements in the historical interaction information to the target processing entity for clustering of the historical interaction information by the target processing entity.
It should be appreciated that the target processing entity may be a processing entity based on suitable information processing technology and may implement the functionality of one or more of text generation, image generation, summarization, encoding, translation, chat bots, and the like. The target processing entity may also be in the form of any other suitable entity. In some examples, the target processing entity may include, for example, a language model.
For example, a target processing entity (e.g., language model) may cluster multiple topics based on semantic analysis of action elements and knowledge elements in the historical interaction information, for example.
In some embodiments, the at least one business component may include, for example, an office component used in the operation of the target object 140. Accordingly, the topic determined by the target processing entity may also be the topic of the work content (e.g., project name, etc.), for example.
Further, the server 130 may obtain a set of topics determined by the target processing entity based on the knowledge elements and action elements. Illustratively, continuing to take the topics of the work content as examples, such a set of topics may include, for example, "X items," "Y items," and the like. In some embodiments, if historical interaction information corresponding to some interaction events cannot be clustered to such topics, it may also be clustered to a preset category, e.g., "others", for example.
In some embodiments, server 130 may, for example, periodically trigger analysis of historical interaction information to determine a corresponding set of topics. For example, the server 130 may trigger a full analysis of the historical interaction information every two weeks to determine a corresponding set of topics, e.g., with a target processing entity.
In some embodiments, server 130 may also process the newly obtained historical interaction information by merging clusters. For example, the server 130 may also obtain second historical interaction information for the target object 140, for example, where the set of topics has been determined based on the first historical interaction information over a first time period (e.g., yesterday ago). Such second historical interaction information may be generated, for example, based on a set of interaction events (also referred to as a second set of interaction events) within a second time period (e.g., yesterday).
Accordingly, the server 130 may determine, for example, a degree of matching of the second set of interaction events to topics in the set of topics. Continuing with the example where the topic collection includes "X item", "Y item", and "other", the server 130 may determine, for example, a degree of matching of a second set of interaction events to "X item" or "Y item" based on historical interaction information corresponding to such second set of interaction events.
The server 130 may determine the degree of matching by, for example, providing the target processing entity with information such as knowledge elements, action elements, etc. of the second set of interaction event corresponding historical interaction information.
Further, the server 130 may determine an association between the second set of interaction events and the set of topics based on the degree of matching.
In particular, in response to the degree of matching of a first interaction event of the second set of interaction events to a target topic of the set of topics reaching a threshold, the server 130 may associate the first interaction event to the target topic. For example, if a certain event in the second set of interaction events matches an "X item" to a threshold, the historical interaction information corresponding to the interaction event may be marked as being associated with the "X item".
And in response to the degree of matching between the second interaction event in the second group of interaction events and the topics except the preset topic in the topic set being smaller than a threshold value, associating the second interaction event to the preset topic. For example, if a certain event in the second set of interaction events matches both "X item" and "Y item" below a threshold, the historical interaction information corresponding to that interaction event may be marked as being associated with a preset topic "other".
In some embodiments, the server 130 may trigger a re-clustering process in response to the number of the plurality of interaction events associated with the preset topic (e.g., "others") reaching the preset number. For example, the server 130 may determine at least one topic based on historical interaction information corresponding to a plurality of interaction events associated with the preset topic. For example, if the number of events included in the "other" topic exceeds a threshold number, the server 130 may, for example, utilize the target processing entity to re-cluster the events in the topic to determine one or more new topics. Further, the server 130 may update the topic set with the determined at least one topic.
Based on such a manner, embodiments of the present disclosure can cluster out corresponding topics according to historical interactions of the target object with business components, thereby facilitating the grooming of the historical interactions of the target object.
Further, server 130 may determine a degree of association of each session with the current work of the target object based on a correlation between unread messages in the session and the set of work topics. For example, the server 130 may utilize a language model to determine the correlation, e.g., degree of matching, between unread messages in a conversation and various topics aggregated.
In some embodiments, server 130 may also provide a set of descriptive terms about the unread message to the target model and obtain correlations determined by the target model, for example. As an example, the server 130 may provide the description items of the unread messages and the aggregated individual topics to the target model, such that the relevance between the description items and the target topics is determined by the target model.
In some embodiments, the descriptive items of the unread message may also include descriptive items associated with a user associated with the unread message, for example. For example, such a descriptive term may indicate a relationship between the user sending the unread message and the current user. Or such descriptive items may also be, for example, at least other users mentioned in the unread message, etc.
In some embodiments, the descriptive term for the unread message may also include, for example, attributes regarding the session in which the unread message is located. For example, the attribute may include a session type of the session, e.g., a meeting group, an item group, and so forth.
Further, the server 130 may determine a degree of association of the session with the target object 140 based on a degree of association between each unread message in the session and a current work of the target object 140, and may determine its corresponding classification based on a comparison of the degree of association with a preset range. For example, where the degree of association is above a particular threshold, the session may be determined to have a higher relevance to the work.
With further reference to fig. 3A, the third category 310-3 may, for example, indicate that the relevance of the corresponding session (e.g., session 340) to the current operation of the target object 140 is below a threshold level. In this case, the content item 315-3 corresponding to the session 340 may, for example, provide descriptive information 345 to indicate that the session 340 is associated with the target object 140 to less than a threshold level. For example, the description information 345 describes, for example, a reason why the session 340 is determined to be of low relevance.
In some embodiments, the recommended content 305 may also include content items 315-4 corresponding to the fourth category 310-4. The fourth classification 310-4 may, for example, indicate that unread messages in the corresponding sessions (e.g., group "A1", "group A2", and "group A3") are determined to be stale messages or invalid messages based on session attributes of the session. For example, the session "A1 group" may be a schedule session created based on a conference schedule, and after the schedule ends for a predetermined period of time, unread messages in the schedule session may be determined as expired messages or invalid messages.
As shown in fig. 3, in some embodiments, terminal device 110 may also present subscription portals 350 in association with recommended content 305. Further, based on the selection of the subscription portal 350, the terminal device 110 may periodically provide recommended content corresponding to the respective period to the target object.
For example, where the target object 140 is subscribed to recommended content (e.g., daily unread message summaries) via the subscription portal 350, the terminal device 110 may, for example, periodically (e.g., a predetermined time of the morning each day) provide the target object 140 with the previous daily unread message summaries.
Further, in the case where the target object has subscribed to the recommended content, the terminal device 110 may present the unsubscribe entrance in association with the recommended content corresponding to the corresponding period, for example. Accordingly, based on the selection for the unsubscribe entrance, the terminal device 110 may stop providing the recommended content corresponding to the subsequent period to the target object 140.
Continuing with the unread message summary as an example, for subsequently received unread message summaries, the target object may trigger the terminal device 110 to stop providing such daily unread message summaries, e.g. by clicking on the corresponding unsubscribe entry.
In some embodiments, the recommended content 305 introduced above may be automatically provided by the terminal device 110, for example. For example, the digital assistant 120 may periodically provide recommended content to the target object 140 for use in sorting unread messages for the target object 140.
In some embodiments, the recommended content 305 may also be provided if 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 may automatically send recommendation information associated with the target object 140 to the terminal device 110.
In some embodiments, the terminal device 110 may also provide the target object 140 with an acquisition portal for acquiring the recommended content 305, and may acquire the recommended information associated with the target object 140 from the server 120 and present the corresponding recommended content 305 based on the selection of the target object 140 for the acquisition portal.
As an example, as shown in fig. 3B, terminal device 110 may provide acquisition portal 360-1 in association with message tag 355 in the navigation bar of the conversation application. For example, when the target object 140 has an unread message, or when the unread message of the target object 140 is greater than a threshold number, the terminal device 110 may present the acquisition portal 360-1 based on a preset operation (e.g., right click operation) of the target object 140 for the message tag 355. As an example, the terminal device 110 may also provide, for example, a portal 360-2 for marking all unread messages as read.
As yet another example, as shown in fig. 3C, the navigation bar may have a greater width than the navigation bar shown in fig. 3B, for example, and accordingly, the terminal device 110 may present the acquisition portal 370 at a preset operation (e.g., a hover operation) of the target object 140 for the message tag 365. Accordingly, upon receiving a selection of the acquisition portal 370, the terminal device 110 may present the recommended content 305 as discussed above.
In some embodiments, terminal device 110 may also provide an acquisition portal, for example, in a session of target object 140 with digital assistant 120. The target object 140 may trigger the presentation of the recommended content 305 by, for example, clicking on the acquisition portal.
In still other embodiments, terminal device 110 may also receive input from target object 140 regarding the collation message, for example, in a session of target object 140 with digital assistant 120, and may present corresponding recommendation content 305 accordingly.
In still other embodiments, terminal device 110 may also support, for example, target object 140 to configure a scope for sessions to be consolidated. Specifically, terminal device 110 may determine a set of target sessions to process based on the configuration operations of target object 140. Accordingly, recommendation information generated based on unread messages in a set of target sessions, and corresponding recommendation content 305 is presented accordingly.
For example, the target object 140 may specify one or more sessions to be consolidated. Accordingly, the generated recommendation content 305 will only involve the sorting of unread messages in the specified session or sessions.
Therefore, the embodiment of the disclosure can automatically sort the unread messages according to the degree of correlation with the work, thereby improving the efficiency of message acquisition.
In some embodiments, the different message classifications in the recommended content may also be determined, for example, based on time information of unread messages in the respective sessions. Fig. 4 illustrates an example interface 400D according to some embodiments of the present disclosure.
As shown in fig. 4, the terminal device 110 may provide recommended content 405. In the recommended content 405, the terminal device 110 may 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 classifications (e.g., classification 410-1, classification 410-2, and classification 410-3).
Unlike the above-mentioned classifications 310-1 to 310-4, the classifications 410-1 to 410-3 may be determined based on time information (transmission time or reception time) of an unread message. For example, the classification 410-1 may correspond to a first time range (e.g., within 7 days); classification 410-2 may correspond to a second time range (7 to 30 days); the classification 410-3 may correspond to a third time range (e.g., more than 30 days).
Similar to the recommended content 305 discussed above, the content items corresponding to each category may indicate a corresponding session and descriptive information about the session. For example, content item 415-1 may indicate description information 425 of session 420 and unread messages in the session 420; content item 415-2 may indicate a description information 435 of session 430 and unread messages in the session 430; content item 415-3 may indicate description information 445 of session 440 and unread messages in the session 440. As yet another example, content item 415-4 may also indicate a group of sessions with a corresponding group.
Therefore, the embodiment of the disclosure can automatically sort the unread messages in a time range, so that the efficiency of message acquisition is improved.
Fig. 5 illustrates a flow chart of a process 500 for message processing according to some embodiments of the present disclosure. Process 500 may be implemented by an appropriate electronic device or combination of electronic devices (e.g., server 130, terminal device 110, or a combination of server 130 and terminal device 110 in fig. 1). For convenience of description, the process 500 is described below with reference to fig. 1, taking the terminal device 110 as an example.
As shown, at block 510, terminal device 110 provides at least one scene in an interactive window of a target object and a digital assistant, the at least one scene including a first scene; wherein the first scenario is configured with corresponding configuration information to perform tasks related to processing unread messages, the configuration information comprising at least one of: scene setting information for describing information related to unread message processing, and plug-in information indicating at least one plug-in for performing tasks related to unread message processing.
In this context, in the context of user interaction with a digital assistant, a "scenario" refers to a collection of tasks of the same type, i.e., one scenario corresponds to multiple tasks of the same type. One or more scenarios may each be configured with corresponding configuration information to perform a respective type of task. For ease of understanding, a brief description of the scenario employed in the user's interaction with the digital assistant will be presented.
The configuration information of the scene includes at least one of: scene setting information and plug-in information. The scene setting information is used to describe information related to a corresponding scene. The plug-in information indicates at least one plug-in for performing a task in a corresponding scenario. As will be discussed below, the configuration information for the scene may also include, for example, an indication of the selected model (where the model is invoked to determine a reply to the user in the corresponding scene), scene guidance information (where the scene guidance information is presented to the user after the corresponding scene is selected), at least one recommendation question for the digital assistant (where the at least one recommendation question is presented to the user for selection after the corresponding scene is selected), and so forth. In some embodiments, the configuration of the scene setting information and the configuration information of the scene may be accomplished, for example, by way of natural language, so that the scene creator may conveniently constrain the output of the model, as well as configure diverse scenes.
The configuration information of the scene includes at least one of: scene setting information and plug-in information. The scene setting information is used to describe information related to a corresponding scene. The scene setting information of the scene may influence the reply of the digital assistant to the user to some extent or may be used to determine the reply of the digital assistant to the user. In some embodiments, scene setting information is used to construct a prompt (prompt) input to provide to a model used in a corresponding scene. The digital assistant's reply to the user is based on the model's output. The scenario set-up information of the scenario may include, for example, a description of the corresponding type of task, a reply style to the digital assistant in the scenario, a definition of a workflow to be performed in the corresponding scenario, a definition of a reply format of the digital assistant in the corresponding scenario, and so on. In some embodiments, the digital assistant will understand the user input via the model and provide a reply to the user based on the output of the model. The model used by the digital assistant may run locally at the terminal device 110 or at a remote server. By constructing a portion of the prompt word input of the model using the scene setting information, the model may be guided to accomplish tasks to be performed in the corresponding scene. In some embodiments, the model may be a machine learning model, a deep learning model, a neural network, or the like. In some embodiments, the model may be based on a Language Model (LM). The language model can have question-answering capability by learning from a large number of corpora. The model may also be based on other suitable models.
The plug-in information indicates at least one plug-in for performing a task in a corresponding scenario. Plug-ins to be used in the corresponding scene can be configured through plug-in information of the scene. In some embodiments, in the corresponding scenario, the plug-in may also invoke the model to complete the corresponding task in the execution of the plug-in. In some embodiments, a plug-in may also invoke an open interface provided by other business components (e.g., document, calendar, meeting, etc. business components) to accomplish corresponding tasks, such as modifying a document, creating a calendar, summarizing a meeting, etc.
In some embodiments, the configuration information of the scene may also include a scene name, description information of the scene, and so on. In some embodiments, terminal device 110 may provide a message card to the user in a session window in which at least some of a set of scenes may be presented. Terminal device 110 may present the scene name of the corresponding scene and/or description information of the scene in association with the scene in the message card. The user may select a scene that meets his own needs, for example, based on the scene name of the scene presented in the message card and/or descriptive information of the scene.
In some embodiments, the configuration information of the scene may also include, but is not limited to: the model selected (where the model is invoked to determine replies to the user in the corresponding scene), scene guidance information (the scene guidance information is presented to the user after the corresponding scene is selected), at least one recommendation question for the digital assistant (the at least one recommendation question is presented to the user for selection after the corresponding scene is selected), any combination of one or more of the foregoing, and so forth. The scene guidance information may be, for example, descriptive information of task instances that can be performed in the scene. In some embodiments, the configuration of the scene setting information and the configuration information of the scene may be accomplished, for example, by way of natural language, so that the scene creator may conveniently constrain the output of the model, as well as configure diverse scenes.
In some embodiments, the configuration information of the scene 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 a user when the scene is selected for interaction to facilitate the user performing interactions with the digital assistant in the corresponding scene. That is, at least one operational control associated with a corresponding scene may be configured by a scene creator during the scene creation process. In some embodiments, the configuration of the scene setting information and the configuration information of the scene may be configured by a scene creator in a natural language manner, for example. In this way, the scene creator can conveniently constrain the output of the model, as well as configure diverse scenes.
In some embodiments, if a scene is selected for interaction by the first user with the first digital assistant, the user's interaction with the digital assistant is performed in the session window based at least on configuration information of the selected scene. Scene setting information, plug-in information, selected models, etc. of the selected scene may be used to guide interactions under the scene.
The specific process of block 510 will be described below with reference to fig. 6A. Fig. 6A illustrates an example interface 600A according to some embodiments of the present disclosure. As shown in fig. 6A, the terminal device 110 provides content 605 in an interactive window in which the target object 140 may be with the digital assistant 120, the content 605 may include at least one scene, e.g., scene 610 and scene 615. Scenario 610 may correspond, for example, to a first scenario for "unread message summary," which may be configured with corresponding configuration information to perform tasks related to processing unread messages. The scene 615 may correspond to a second scene for "content understanding", for example. The user may also select other more scenes, for example, through control 620.
With continued reference to fig. 5, in response to a preset operation of the target object on the first scene, the terminal device 110 performs an interaction of the target object with the digital assistant based at least on configuration information of the first scene, at block 520.
As an example, in case the scene 610 is selected, the terminal device 110 may present an interface 600B as shown in fig. 6B. In interface 600B, digital assistant 120 may provide content 640, which content 640 may include a set of recommendation questions 645, 650, and 655. Such different recommendation questions may correspond to different interaction requests.
For example, recommendation question 645 may be used to trigger the acquisition of consolidated content for all unread messages. The recommendation question 650 may trigger the acquisition of consolidated content for unread messages in a specified session. The recommendation questioning 655 may trigger subscription to the consolidated content for unread messages.
As an example, in the event that the user selects recommendation question 645, the corresponding input content 660 may be sent to the digital assistant. Further, as shown in fig. 6C, the terminal device 110 may provide the generated recommended content 665 for all unread messages.
The specific content and the generation process of the recommended content 665 can be referred to the content described above with reference to fig. 2 to 4, and will not be described here.
Based on the above-discussed processes, embodiments of the present disclosure may provide a user with a scenario for sorting unread messages, thereby improving the user's efficiency of sorting unread messages.
Example apparatus and apparatus
Fig. 7A illustrates a schematic block diagram of an apparatus 700A for message processing according to some embodiments of the present disclosure. The apparatus 700A may be implemented as or included in the server 130, the terminal device 110, or a combination of the server 130 and the terminal device 110 of fig. 1. The various modules/components in apparatus 700A may be implemented in hardware, software, firmware, or any combination thereof.
As shown, the apparatus 700A includes an information acquisition module 710 configured to acquire recommendation information associated with a target object; and a content providing module 720 configured to provide recommended content to the target object based on the recommendation information, wherein the recommended content comprises at least a first portion corresponding to the first message classification, the first portion comprising 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 descriptive information about unread messages in the first set of conversations, wherein the first message classification is determined based on a first degree of association of the unread messages in the first set of conversations with 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.
In some embodiments, the recommended content further includes a second portion corresponding to a second message classification, the second portion including a second set of content items corresponding to the second message classification, the second set of content items generated based on a second set of sessions associated with the second message classification.
In some embodiments, a second degree of association of a second set of content items corresponding to a second message classification with a current work of the target object is below a threshold degree, and the second set of content items includes second descriptive information about the second degree of association of the second set of sessions with the target object being below the threshold degree.
In some embodiments, the second message classification indicates that unread messages in the second set of sessions are determined to be stale messages or invalid messages based on session attributes of the second set of sessions.
In some embodiments, the first degree of association is determined based on the following process: acquiring 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 a set of work topics associated with a set of interaction events based on the historical interaction information; and determining a first degree of association of the first group of sessions with the current work of the target object based on the correlation between the unread messages in the first group of sessions and the set of work topics.
In some embodiments, the first degree of association is also determined based on the following process: a set of descriptive terms about the unread message is provided to the target model to obtain a correlation determined by the target model.
In some embodiments, the descriptive information indicates at least one of: summary content regarding a set of unread messages in a corresponding session of the first set of sessions; to-Do content generated based on a set of unread messages.
In some embodiments, the apparatus 700A further comprises an inlet providing module configured to: providing a first portal for marking as read a set of unread messages in a corresponding session; providing a second inlet, wherein the second inlet is used for generating a reminder corresponding to the content to be handled; or providing a third portal for displaying a session window for the corresponding session.
In some embodiments, the apparatus 700A further comprises a subscription module configured to: presenting a subscription portal in association with the recommended content; and periodically providing recommended content corresponding to the respective period to the target object based on the selection of the subscription portal.
In some embodiments, the apparatus 700A further comprises a unsubscribing module configured to: presenting an unsubscribe entrance in association with recommended content corresponding to the respective time period; and stopping providing recommended content corresponding to the subsequent period to the target object based on the selection of the unsubscribe entrance.
In some embodiments, the information acquisition module 710 is further configured to: 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.
In some embodiments, the information acquisition module 710 is further configured to: providing an acquisition portal for acquiring recommended content; and acquiring recommendation information associated with the target object based on a preset operation for the acquisition portal.
In some embodiments, the information acquisition module 710 is further configured to: providing an acquisition portal in association with a message tag in a navigation bar of a conversation application; or provide an acquisition portal in a session of the target object with the digital assistant.
In some embodiments, the information acquisition module 710 is further configured to: determining a set of target sessions to be processed based on configuration operations of the target objects; and obtaining recommendation information associated with the target object, wherein the recommendation information is generated based on unread messages in the set of target sessions.
Fig. 7B illustrates a schematic block diagram of an apparatus 700B for message processing according to some embodiments of the present disclosure. The apparatus 700B may be implemented as or included in the server 130, the terminal device 110, or a combination of the server 130 and the terminal device 110 of fig. 1. The various modules/components in apparatus 700B may be implemented in hardware, software, firmware, or any combination thereof.
As shown, the apparatus 700B includes a scene providing module 730 configured to provide at least one scene including a first scene in an interactive window of a target object and a digital assistant; wherein the first scenario is configured with corresponding configuration information to perform tasks related to processing unread messages, the configuration information comprising at least one of: scene setting information for describing information related to unread message processing, plug-in information indicating at least one plug-in for executing tasks related to unread message processing; and an interaction module 740 configured to perform interaction of the target object with the digital assistant based at least on the configuration information of the first scene in response to a preset operation of the target object on the first scene.
In some embodiments, the configuration information further includes at least one of: an indication of the selected model, the model being invoked to determine a reply to the target object in the first scenario; scene guidance information, which is presented to the target object after the first scene is selected; or at least one recommendation question for the digital assistant, the at least one recommendation question being presented to the target object for selection after the first scene is selected.
In some embodiments, the scene setting information is used to construct a hint word input to provide to a model used in the first scene, the reply to the target being based on the output of the model.
In some embodiments, the interaction module 740 is further configured to: providing, by the digital assistant, recommended content, wherein the recommended content includes at least a first portion corresponding to the first message classification, the first portion 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 descriptive information about unread messages in the first set of conversations.
In some embodiments, the first message classification is determined based on a first degree of association of unread messages in the first set of sessions with the current work of the target object; or the first message classification is determined based on time information of unread messages in the first set of sessions.
Electronic device 800 typically includes multiple computer storage media. Such a medium may be any available media that is accessible by electronic device 800, including, but not limited to, volatile and non-volatile media, removable and non-removable media. The memory 820 may be volatile memory (e.g., registers, cache, random Access Memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 830 may be a removable or non-removable medium and may include machine-readable media such as flash drives, magnetic disks, or any other medium that may be used to store information and/or data and that may be accessed within electronic device 800.
The electronic device 800 may further include additional removable/non-removable, volatile/nonvolatile storage media. Although not shown in fig. 8, a magnetic disk drive for reading from or writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data medium interfaces. Memory 820 may include a computer program product 825 having one or more program modules configured to perform the various methods or acts of the various embodiments of the present disclosure.
The communication unit 840 enables communication with other electronic devices through a communication medium. Additionally, the functionality of the components of the electronic device 800 may be implemented in a single computing cluster or in multiple computing machines capable of communicating over a communications connection. Thus, the electronic device 800 may operate in a networked environment using logical connections to one or more other servers, a network Personal Computer (PC), or another network node.
The input device 850 may be one or more input devices such as a mouse, keyboard, trackball, etc. The output device 860 may be one or more output devices such as a display, speakers, printer, etc. The electronic device 800 may also communicate with one or more external devices (not shown), such as storage devices, display devices, etc., with one or more devices that enable a user to interact with the electronic device 800, or with any device (e.g., network card, modem, etc.) that enables the electronic device 800 to communicate with one or more other electronic devices, as desired, via the communication unit 840. Such communication may be performed via an input/output (I/O) interface (not shown).
According to an exemplary implementation of the present disclosure, a computer-readable storage medium having stored thereon computer-executable instructions, wherein the computer-executable instructions are executed by a processor to implement the method described above is provided. According to an exemplary implementation of the present disclosure, there is also provided a computer program product tangibly stored on a non-transitory computer-readable medium and comprising computer-executable instructions that are executed by a processor to implement the method described above.
Various aspects of the present disclosure are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus, devices, and computer program products implemented according to the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer readable program instructions may be provided to a processing unit of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processing unit of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable medium having the instructions stored therein includes an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various implementations of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing description of implementations of the present disclosure has been provided for illustrative purposes, is not exhaustive, and is not limited to the implementations disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various implementations described. The terminology used herein was chosen in order to best explain the principles of each implementation, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand each implementation disclosed herein.