Method, apparatus, device and storage medium for information processing

Abstract

According to an embodiment of the present disclosure, a method, an apparatus, a device and a storage medium for information processing are provided. The method comprises receiving a first interaction message of a user with a digital assistant in a first sub-conversation, the first interaction message being from the user; determining a first information set associated with a main conversation between the user and the digital assistant based on a main conversation identifier of the main conversation; determining a sub-conversation identifier of the first sub-conversation based on the first information set; determining a first topic identifier of a first topic to which the first interaction message belongs based on the sub-conversation identifier; obtaining stored context information of the first topic based on the first topic identifier; and obtaining a first reply message of the digital assistant to the first interaction message based on the context information. Thus, in the case that the user and the digital assistant have a multi-round conversation under the same topic, the digital assistant can perceive the same context. This is conducive to providing an efficient assistance experience to the user.

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 information processing. BACKGROUND

[0002] With the development of information technology, various terminal devices can provide various services to people in work and life, etc. For example, an application providing services can be deployed in a terminal device. The terminal device or its application can provide a user with an assistant type function to assist the user in using the terminal device or the application to complete a task. How to make such an assistant type function better serve the user is a technical problem currently explored. SUMMARY

[0003] In a first aspect of the present disclosure, a method for information processing is provided. The method comprises: receiving a first interaction message of a user with a digital assistant in a first sub-conversation, the first interaction message being from the user; determining a first information set associated with a main conversation between the user and the digital assistant based on a main conversation identifier of the main conversation; determining a sub-conversation identifier of the first sub-conversation based on the first information set; determining a first topic identifier of a first topic to which the first interaction message belongs based on the sub-conversation identifier; obtaining stored context information of the first topic based on the first topic identifier; and obtaining a first reply message of the digital assistant to the first interaction message based on the context information.

[0004] In a second aspect of the present disclosure, a method for information processing is provided. The method comprises: receiving an interaction message of a user with a digital assistant in a conversation, the interaction message being from the user and referencing a historical message in the conversation; obtaining a stored information set of a message dimension associated with the historical message based on a message identifier of the historical message; determining a target topic identifier of a topic to which the interaction message belongs as a topic identifier indicated in the information set of the message dimension; obtaining stored context information of the topic based on the target topic identifier; and obtaining a reply message of the digital assistant to the interaction message based on the context information.

[0005] In a third aspect of the disclosure, an apparatus for information processing is provided. The apparatus includes: a message receiving module configured to receive a first interaction message of a user with a digital assistant in a first sub-conversation, the first interaction message being from the user; a first information set determining module configured to determine a first information set associated with a main conversation between the user and the digital assistant based on a main conversation identifier of the main conversation; a sub-conversation identifier determining module configured to determine a sub-conversation identifier of the first sub-conversation based on the first information set; a topic identifier determining module configured to determine a first topic identifier of a first topic to which the first interaction message belongs based on the sub-conversation identifier; a context information obtaining module configured to obtain stored context information of the first topic based on the first topic identifier; and a reply message obtaining module configured to obtain a first reply message of the digital assistant to the first interaction message based on the context information.

[0006] In a fourth aspect of the disclosure, an apparatus for information processing is provided. The apparatus includes: a message receiving module configured to receive an interaction message of a user with a digital assistant in a conversation, the interaction message being from the user and referencing a historical message in the conversation; an information set obtaining module configured to obtain a stored information set of a message dimension associated with the historical message based on a message identifier of the historical message; a topic identifier determining module configured to determine a topic identifier indicated in the information set of the message dimension as a target topic identifier of a topic to which the interaction message belongs; a context information obtaining module configured to obtain stored context information of the topic based on the target topic identifier; and a reply message obtaining module configured to obtain a reply message of the digital assistant to the interaction message based on the context information.

[0007] In a fifth aspect of the 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 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 disclosure, nor is it used to limit the scope of the disclosure. Other features of the disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0010] The above-described and other features, advantages, and aspects of the present disclosure will become more apparent as various embodiments of the present disclosure are described in greater detail below. In the drawings, like reference numerals refer to like elements throughout:

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

[0012] Figures 2A-2E A schematic diagram illustrating an example interface of a main conversation window and a sub-conversation window according to some embodiments is shown;

[0013] Figure 3 A schematic diagram illustrating use of multiple sets of information of multiple dimensions in a user’s conversation with a digital assistant according to some embodiments is shown;

[0014] Figure 4 An example process of passing interaction messages between a user and a digital assistant according to some embodiments is shown;

[0015] Figure 5 A schematic diagram illustrating a process of topic switching according to some embodiments is shown;

[0016] Figure 6 A schematic diagram illustrating a process of accessing a sub-conversation according to some embodiments is shown;

[0017] Figure 7 A flow diagram illustrating a process of information processing according to some embodiments is shown;

[0018] Figure 8 Another flow diagram illustrating a process of information processing according to some embodiments is shown;

[0019] Figure 9 A block diagram of an apparatus for information processing according to some embodiments is shown;

[0020] Figure 10 Another block diagram of an apparatus for information processing according to some embodiments is shown; and

[0021] Figure 11 A block diagram of a device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0022] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be implemented in various forms and should not be interpreted as being limited to the embodiments set forth herein, but rather, these embodiments are provided so as to more completely and thoroughly understand the present disclosure. It is understood that the drawings and embodiments of the present disclosure are for exemplary purposes only and are not intended to limit the scope of protection of the present disclosure.

[0023] In the description of embodiments of the present disclosure, the term "comprising" and its conjugations should be understood to encompass the meaning of "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions can also be included below.

[0024] In this document, unless explicitly stated, performing a step "in response to A" does not mean performing the step immediately after A, but can include one or more intermediate steps.

[0025] It can be understood that the data involved in the technical solutions of the present disclosure (including but not limited to the data itself, the obtaining, use, storage or deletion of the data) should comply with the requirements of relevant laws and regulations and relevant provisions.

[0026] 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 through appropriate means, wherein the relevant user can include any type of right subject, such as an individual, an enterprise or a group.

[0027] For example, in response to receiving the active request of the user, a prompt information is sent to the relevant user to explicitly prompt the relevant user that the operation requested to be performed will require the information of the relevant user to be obtained and used, so that the relevant user can voluntarily choose whether to provide the information to the software or hardware such as electronic device, application program, server or storage medium, etc. performing the operation of the technical solutions of the present disclosure according to the prompt information.

[0028] As an optional but non-limiting implementation manner, in response to receiving the active request of the relevant user, the manner of sending the prompt information to the relevant user can be, for example, the manner of pop-up window, and the prompt information can be presented in the form of text in the pop-up window. In addition, the pop-up window can also carry selection controls for the user to select "agree" or "disagree" to provide information to the electronic device.

[0029] It can be understood that the above notification and user authorization obtaining process is only illustrative and does not limit the implementation of the present disclosure, and other ways that meet relevant laws and regulations can also be applied to the implementation of the present disclosure.

[0030] Figure 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, an office suite 120 is installed in a terminal device 110. A user 140 can interact with the office suite 120 via the terminal device 110 and / or an attached device of the terminal device 110. The office suite 120 is capable of providing integration of multiple applications or components to the user 140. These applications can be as application modules in the office suite 120. The applications integrated in the office suite 120 are also sometimes referred to as “office applications”, “office components”, “collaborative office platforms”, etc. As an example, the applications integrated in the office suite 120 can include, but are not limited to, one or more of the following: a chat application (also referred to as an instant messaging (IM) application), a document application, an audio and video conferencing application, a mail application, a calendar application, a schedule application, a task application, an objective and key result (OKR) application.

[0031] In some embodiments, the office suite 120 can be downloaded and installed in the terminal device 110 as an application. In some embodiments, the office suite 120 can also be accessed by other means, such as by web page access, etc.

[0032] In the environment 100, Figure 1 If the office suite 120 is started, the terminal device 110 can present an interface 150 of the office suite 120 to the user 140 in the environment 100. The interface 150 is also sometimes referred to as a client interface. The interface 150 can include various types of interfaces that can be provided by the office suite 120, such as a conversation interface for presenting chat content, a video conference interface, a file sharing interface, etc.

[0033] In some embodiments, the terminal device 110 communicates with the server 130 to enable provisioning of services of the office suite 120. The terminal device 110 can be any type of mobile terminal, fixed terminal, or portable terminal including a mobile handset, a tablet 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 thereof, including an accessory or peripheral device for the foregoing, or any combination thereof. In some embodiments, the terminal device 110 can also be capable of supporting any type of interface for user interaction (such as a "wearable" circuit, etc.). The server 130 can be any type of computing system / server capable of providing computing capabilities, including but not limited to a mainframe, an edge computing node, a computing device in a cloud environment, etc.

[0034] It should be appreciated that the structure and functionality of the various elements in the environment 100 are described for illustrative purposes only and without implying any limitation on the scope of the present disclosure. For example, embodiments of the present disclosure can be applied to any suitable application(s) without being limited to the office suite.

[0035] As briefly mentioned earlier, a digital assistant can be provided to a user to help the user to accomplish a target task using a terminal device or an application. In embodiments of the present disclosure, a digital assistant is configured for the user 140. The digital assistant can be implemented in any suitable form. In some embodiments, the digital assistant of the user 140 can interact with the user 140 as a contact of the user 140. Such a digital assistant can also correspond to the user 140 uniquely. In other words, the digital assistant of the user 140 can be specific or exclusive to the user 140. If the user 140 is an individual or a person, such a digital assistant can be considered as a personal digital assistant. It can be appreciated that the digital assistant in embodiments of the present disclosure is granted access to data based on authorization of the user 140.

[0036] It should be appreciated that the "unique correspondence" or similar expressions in the present disclosure are not intended to limit that the digital assistant will be updated accordingly based on the interaction process between the user 140 and the digital assistant.

[0037] In embodiments of the present disclosure, after the digital assistant is woken up by a preset application, the user 140 interacts with the digital assistant through a main session. The interaction window corresponding to the main session can be referred to as a main session window. As an example, the preset application can be an IM application in the office suite. In other examples, the preset application can also be other applications or components.

[0038] Reference is made to Figure 2AAn example of a main conversation window in the office suite is described. The terminal device presents an interface 200A of the office suite. The interface 200A includes a navigation bar 230, in which a plurality of application entry controls and a plurality of page access entries are displayed. By selecting the entry controls and access entries, the corresponding application or page can be activated for browsing or operation. In this example, the chat application is activated. Accordingly, a feed page 210 of the chat application, i.e., a conversation entry list, is presented in the interface 200A. A conversation entry item 211 of the user with the digital assistant (“XX Assistant” in FIG. 2) is displayed in the feed page 210. The user can click the conversation entry item 211 of the “XX Assistant” to present a main conversation window 220.

[0039] In embodiments of the present disclosure, the conversation entry with the digital assistant can also be in the contact list. The user 140 can open the main conversation window 220 with the digital assistant by triggering the conversation entry of the digital assistant in the contact list.

[0040] In the above example and the following examples, the digital assistant is shown to have the name of “XX Assistant”, but it should be understood that this is only exemplary and is not intended to limit the scope of the present disclosure. In embodiments of the present disclosure, the digital assistant can have any suitable name, which can be customized by the user 140.

[0041] In embodiments of the present disclosure, the digital assistant can also be awakened and interacted with through other applications other than the preset application. After the digital assistant is awakened through these non-preset applications, the user can interact with the digital assistant through a sub-conversation. The interaction window corresponding to the sub-conversation can be referred to as a sub-conversation window. The user can invoke the digital assistant through a page in a document application, and then interact with the digital assistant through a sub-conversation.

[0042] Reference Figure 2B An example of a sub-conversation window in the office suite is described. The terminal device presents an interface 200B of the office suite. In this example, a document page 240 is presented in the interface 200B. In the document page 240, an option or control 241 related to the digital assistant is presented. The user can click the control 241 to awaken the digital assistant, thereby presenting a sub-conversation window 250. In this example, the sub-conversation window 250 displays a prompt message “Start collaborating with you – based on AAAA”. Further, the user can interact with the digital assistant through the sub-conversation window 250. Interaction messages can be displayed in the sub-conversation window 250 (as indicated by the dashed box 251).

[0043] The above describes the sub-conversation of the user with the digital assistant using the document application as an example. It should be understood that the user can awaken the digital assistant through any other suitable application.

[0044] In some embodiments, the interaction messages in the sub-conversation window can be displayed in the main conversation window in an aggregated form. As an example, referring to Figure 2B and Figure 2C the interaction messages in the sub-conversation window 250 presented in the interface 200B (as indicated by the dashed box 251) are shown in the main conversation window 220 of the interface 200C in an aggregated form of message records (as indicated by the dashed box 260). Here, the aggregated form can refer to the message records in the sub-conversation window 250 are collectively shown, e.g., collectively shown in the location indicated by the dashed box 260, without being inserted in other messages. As such, the interaction messages between the user and the digital assistant can be uniformly recorded, and thus can be traced back. This facilitates to provide an efficient assistance experience to the user.

[0045] In embodiments of the present disclosure, through the main conversation and the sub-conversation, the user and the digital assistant can interact on different topics. As an example, referring to Figure 2D the control 272 for starting a new topic is displayed in the sub-conversation window 270. If the user 140 clicks the control 272, the topic involved in the interaction in the dashed box 271 can be ended, and a new topic can be started. Accordingly, the message records of the sub-conversation window 270 shown in the main conversation window can include interaction messages on different topics, and the messages under different topics can be distinguished. As an example, referring to Figure 2E the message records on one topic in the sub-conversation window 270 are shown in the area 281 of the main conversation window 220, and the message records on another topic are shown in the area 282. The new topic is separated from the previous topic by the identification 283 that a new topic is started.

[0046] In this way, the user 140 can start a conversation (i.e., a sub-conversation) with the digital assistant in various business scenarios of the office suite 120, and synchronize the interaction messages in the conversation to the conversation (i.e., the main conversation) between the user 140 and the digital assistant. As such, the conversation context information under different sub-conversation scenarios can be kept relatively independent, and can be synchronized to the main conversation, thereby providing a consistent and complete interaction experience for the user 140.

[0047] For the same topic, multiple rounds of conversation between the user and the digital assistant can be needed. In some scenarios, more natural conversation and communication between the user and the digital assistant can be achieved by using deep learning and natural language processing technology. In this case, the topic needs to perceive the context information of the multiple rounds of conversation between the user and the digital assistant. Generally, an office suite can provide multiple applications, such as a chat application (also referred to as a message application), a document application, a table application, a mailbox application, and the like. The digital assistant can be invoked to have a conversation with the user in the process of providing services corresponding to each application. In order to store the context information, a mechanism with scalability and universality needs to be designed for the main session or the sub-session. This mechanism needs to support topic isolation in the main session and the sub-session, so that the conversation between the user and the digital assistant in different application scenarios has a relatively independent context.

[0048] To this end, an embodiment of the present disclosure provides a scheme for information processing. In the scheme, when an interaction message from the user in a sub-session is received, a topic identifier of a topic to which the interaction message belongs is determined based on one or more sets of information in a dimension (for example, a set of information in a main session dimension, a set of information in a sub-session dimension, and the like). Based on the topic identifier, the context information of the topic stored can be obtained. A reply message of the digital assistant to the interaction message is obtained based on the obtained context information. According to various embodiments of the present disclosure, the topic identifier is maintained by using one or more sets of information in a dimension, and the context information is stored according to the topic identifier. In this way, in the case that the user and the digital assistant have multiple rounds of conversation under the same topic, the digital assistant can perceive the same context. Thus, the digital assistant can help to make an accurate response to the interaction message of the user, so that an efficient assistance experience can be advantageously provided to the user.

[0049] The example embodiments of the present disclosure will be described in detail below. As described above with reference to Figures 2A-2E The conversation between the user 140 and the digital assistant can involve one or more of the following: a main session, a sub-session, a topic, and a message.

[0050] The main session between the user 140 and the digital assistant can be implemented as a one-on-one group. In this main session, each message in the conversation between the user 140 and the digital assistant has a certain time sequence, and the messages are also sequentially arranged and displayed according to time. In order to keep the conversation between the user 140 and the digital assistant in the same context on this single timeline, and avoid the digital assistant answering the wrong question due to message confusion. In an embodiment of the present disclosure, a set of information in a main session dimension can be maintained, which can be indexed by a main session identifier (ID). The set of information in the main session dimension can record various appropriate information from the perspective of the main session. For example, a data structure can be maintained in the main session dimension.

[0051] In addition to the information set of the main session dimension, in order to solve the context awareness on a certain message, in some embodiments of the present disclosure, an information set of the message dimension can be maintained, which can be indexed by the message ID. Such a message can be sent by the user 140 or sent by the digital assistant.

[0052] In some embodiments, when the digital assistant replies to the user's message, the dimension of the machine learning model can only perceive the topic. For this purpose, an information set of the topic dimension can be maintained, which can be indexed by the topic ID. The information set of the topic dimension can record various appropriate information from the perspective of the topic, such as various related identifiers. For example, a data structure can be maintained on the topic dimension. From the information set of the topic dimension, other context-based information such as the main session ID, the user ID, the message ID, etc. can be read. In this way, the destination of the reply message of the digital assistant can be determined, that is, it is known which message of which user is replied to, and where the message is sent to.

[0053] In the office suite 120, the sub-session of the user 140 and the digital assistant is also an important form of interaction. For this purpose, an information set of the sub-session dimension can be maintained, which can be indexed by the sub-session ID. The information set of the sub-session dimension can record various appropriate information from the perspective of the sub-session, such as various related identifiers. For example, a data structure can be maintained on the sub-session dimension.

[0054] The information sets of the main session dimension, the sub-session dimension, the topic dimension and the message dimension are outlined above. The information sets of these different dimensions can adopt any suitable data structure, and can include any appropriate fields. Table 1 describes an example of the information set.

[0055] Table 1

[0056]

[0057]

[0058] It should be understood that the number, name, etc. of the fields shown in Table 1 are exemplary and are not intended to be any limitation. In embodiments of the present disclosure, the information set can include any identifier information, indication information, etc. related to the conversation of the user and the digital assistant.

[0059] Figure 3 A schematic diagram 300 of using multiple dimensions of information sets in a conversation of a user and a digital assistant according to some embodiments is shown. For ease of discussion, the following describes the schematic diagram 300 in conjunction with Figure 1 and Figures 2A-2E Figure 3 ​The illustrated embodiments. It should be appreciated that this is merely an illustrative and not a restrictive.

[0060] At the terminal device 110, under the same topic, a multi-round conversation can be conducted between the user 140 and the digital assistant. In some embodiments, the topic can be conducted in a sub-conversation triggered by a certain application. In this article, such a sub-conversation can also be referred to as a "first sub-conversation".

[0061] In this case, the server 130 can receive the interaction message of the user 140 and the digital assistant in the first sub-conversation from the terminal device 110, for example, the interaction message 310. For the convenience of description, the interaction message 310 can also be referred to as the first interaction message. The interaction message 310 is from the user 140. The server 130 can determine the information set 316 associated with the main conversation based on the main conversation identifier 314 of the main conversation between the user 140 and the digital assistant, also referred to as the first information set 316 or the information set 316 of the main conversation dimension. For example, the information set of the main conversation dimension can be queried with the main conversation identifier 314 as the index. If the information set corresponding to the main conversation identifier 314 is queried, it can be taken as the information set 316 of the main conversation dimension. If the information set associated with the main conversation identifier 314 is not queried, it means that it is an initialization process. Accordingly, the topic identifier can be created, and the information set 316 associated with the main conversation identifier 314 can be created, wherein the created topic identifier is stored.

[0062] After obtaining the information set 316 of the main conversation dimension, the sub-conversation identifier 318 of the first sub-conversation can be determined based on the information set 316 of the main conversation dimension. For example, the sub-conversation identifier 318 can be determined according to the "ThreadID" field shown in Table 1.

[0063] Next, the server 130 can determine the topic identifier of the topic (also referred to as the "first topic") to which the first interaction message belongs based on the sub-conversation identifier 318, also referred to as the "first topic identifier" 322. In some embodiments, the information set of the sub-conversation dimension (also referred to as the second information set) 320 can be queried by the sub-conversation identifier 318. For example, the information set of the sub-conversation dimension 320 associated with the first sub-conversation can be queried based on the sub-conversation identifier 218 of the first sub-conversation. If the information set of the sub-conversation dimension 320 is queried, the identifier of the current topic indicated in the information set of the sub-conversation dimension 320 can be determined as the first topic identifier 322. For example, the "SessionID" shown in Table 1 can be determined as the first topic identifier 322.

[0064] If the information set 320 of the sub-session dimension is not queried, a first topic identification 322 of the first topic and the information set 320 of the sub-session dimension can be created and the first topic identification 322 is included in the information set 320 of the sub-session dimension for storage. In this case, the stored first topic identification 322 is used as the identification of the current topic of the first sub-session.

[0065] In the embodiments described above, the topic identification is determined from the information set of the sub-session dimension. Alternatively, in some embodiments, the topic identification 322 can be determined directly from the information set of the main session dimension 316. For example, the identification of the latest topic of the conversation (including the main session and the sub-session) between the user and the digital assistant can be stored in the information set of the main session dimension 316.

[0066] Based on the first topic identification 322, the server 130 can obtain the stored context information 326 of the first topic. For example, the context information 326 about the first topic can be obtained by querying a database or a memory for storing the context information. Then, based on the context information 326, the server 130 can obtain a reply message (also referred to as “first reply message”) 327 of the digital assistant to the first interaction message. For example, the context information 326 together with the interaction message 310 can be sent to a machine learning model, and the reply message 327 is generated by the machine learning model.

[0067] As Figure 3 shown in FIG. 3, in some embodiments, the interaction message 310 and the reply message 327 can be stored as part of the context information 326. In this way, the context information about the first topic can be constantly updated to facilitate providing context for the subsequent rounds of the conversation.

[0068] In some embodiments, in the case where the first reply message is obtained, based on the first topic identification 322, the server 130 can determine an information set of the topic dimension (also referred to as “third information set”) 324 associated with the first topic. Based on the information set of the topic dimension, the destination of the reply message 327 can be determined. In this way, it can be determined which message of which user the digital assistant is currently replying to, and to which terminal device the replied message is to be sent.

[0069] As mentioned above, in order to solve the problem of context awareness from the perspective of messages, an information set of the message dimension can be maintained. In some embodiments, as Figure 3As shown, a message-dimension information set (also referred to as "fourth information set") 312 can be generated and stored based on the interaction message 310. That is, an information set can be maintained for the message sent by the user to store the relevant identification, indication, etc. For example, the message-dimension information set 312 can include various information such as, but not limited to, the message identification of the interaction message 310, the session identification 318, and the first topic identification 322.

[0070] Alternatively or additionally, in some embodiments, a message-dimension information set (also referred to as "fifth information set") 328 associated with the reply message 327 can be generated and stored. That is, an information set can be maintained for the message sent by the digital assistant to store the relevant identification, indication, etc. The information set includes at least the message identification of the reply message 327, the session identification 318, and the first topic identification 322.

[0071] In such embodiments, information sets of message-dimension are maintained for the messages sent by the user and / or the messages sent by the digital assistant. With such information sets of message-dimension, a topic can be re-opened after the topic is closed. Specifically, in some embodiments, after a second topic different from the first topic is opened, the server 130 can receive a second interaction message from the user 140. If the second interaction message references at least one of the first interaction message 310 and the first reply message 327, the server 130 can query the information set of message-dimension associated with the referenced message(s) based on the message identification of the referenced message(s). If the first topic identification 322 is determined from the queried information set of message-dimension, the server 130 can obtain the stored context information 326 associated with the first topic identification 322 based on the first topic identification, and generate a second reply message for the second interaction message based on the obtained context information 326. In this way, the first topic that has been closed can be re-opened.

[0072] It should be appreciated that, as described above with reference to Figure 2E the messages in the sub-session can be recorded into the main session. Thus, the second interaction message used to re-open the first topic described herein can come from a sub-session in which the first topic originally occurs, or from a main session between the user 140 and the digital assistant. In other words, even if the sub-session is closed, the user 140 can re-open the topic in the sub-session through message records in the main session.

[0073] To more clearly understand the information processing scheme of the present disclosure, reference is made to Figure 4 An example process 400 of passing an interaction message between a client and a server is described.

[0074] InFigure 4 In the example of FIG. 4, the client 410 can be running at the end device 110 for implementing the office suite 120. The server 460 can be running at the server 130. By way of example only, the server 460 can include, but is not limited to, a message service 420, a digital assistant service 430, a machine learning service 440, and an interface 450. The message service 420 can be used to provide services related to a message application in the office suite 120, for example. The digital assistant service 430 can be used to provide services related to a digital assistant, for example. The machine learning service 440 can utilize any suitable machine learning model to provide various suitable services in the office suite 120, for example, which can utilize a machine learning model when generating a digital assistant’s answer to a user. The interface 450 can be an open application program interface, for example.

[0075] In particular, Figure 4 An example process 400 is shown for a single round of conversation between the user 140 and the digital assistant. The user 140 sends a message to the digital assistant through the client 410. As Figure 4 As shown, the client 410 sends (462) the message from the user 140 to the message service 420. The message service 420 determines (464) whether the message is received successfully. If so, the message service 420 sends (466) a notification to the client 410 that the message is sent successfully. The message service 420 then sends (468) the message received from the client 410 to the digital assistant service 430, and instructs the digital assistant service 430 that the user 140 sent a message to the digital assistant.

[0076] The digital assistant service 430 can determine (470) a topic identification of a topic to which the message belongs, and obtain context information of the topic based on the topic identification. The determination of the topic identification can be as described above with reference to Figure 3As described. For example, before the message is passed to the machine learning service 440, the digital assistant service 430 can read a set of information of the primary session dimension, such as the structure shown in Table 1, with the primary session identification (e.g., ChatID) as the index. The digital assistant service 430 can obtain the topic ID within the set of information. Thereafter, the digital assistant service 430 can pass the message to the machine learning service 440, along with other data, etc. The machine learning service 440 can perceive the same topic ID to determine the corresponding semantic context. If the topic ID of the primary session dimension does not exist in the memory or database, it can be considered as an initialized state. At this time, an empty topic ID can be passed to the machine learning service 440, and a new topic ID can be generated and returned by the machine learning service 440. Subsequently, the digital assistant service 430 can store the set of information of the primary session dimension, which includes the generated topic ID. In the subsequent dialog, e.g., the next round of dialog, the stored topic ID can be obtained. In this way, for the same topic, the machine learning service 440 can perceive the same context information, which improves consistency and accuracy.

[0077] Continuing Figure 4 After obtaining the topic ID, the digital assistant service 430 can send (472) information related to the context information, such as but not limited to, the message text, the topic identification, the token, etc., to the machine learning service 440.

[0078] The machine learning service 440 can extract the topic ID from the received information and return (474) to the digital assistant service 430, which can indicate that the information about the topic ID has been successfully received. Additionally, in some embodiments, the machine learning service 440 can send (476) the token extracted from the above-mentioned received information to the interface 450 for the application, to authenticate whether the message is a legal message or has the right to process the message, etc. Accordingly, the interface 450 can perform the corresponding authentication and send (478) the authentication result to the machine learning service 440.

[0079] The machine learning service 440 can obtain (480) the message to be replied to the user 140 by performing some processing on the context information, such as can utilize a machine learning model, etc. In some embodiments, in the reply process, the message to be replied can be returned (482) to the message service 420 in a streaming form, and then pushed (484) to the client 410 by the message service 420.

[0080] In the case of multiple rounds of dialog, a process similar to the process 400 can be performed for each round of dialog.

[0081] The above reference Figure 3This describes how topics occurring within a separate session can be restarted. Similarly, topics within the main session can be restarted after the session ends. See below for reference. Figure 5 To describe an example. For example... Figure 5 As shown, messages 511, 512, and 513 are messages in the main session and belong to topic 1, identified as "Topic ID 1," while messages 521 and 522 are messages in the main session and belong to topic 2, identified as "Topic ID 2." In some embodiments, the main session between user 140 and the digital assistant can be implemented as a one-on-one chat group. In this main session, the messages in the chat between user 140 and the digital assistant have a defined time sequence, and these messages are also displayed sequentially according to time, such as... Figure 3 As shown.

[0082] Messages 501 and 502 belong to the same topic within a sub-session, while messages 503 and 504 belong to a different topic within the same sub-session. These two sub-sessions can be the same sub-session or different sub-sessions. Figure 5 As shown, messages in the main session expand vertically, while messages in the sub-sessions expand horizontally.

[0083] After topic 1 ends and topic 2 begins, message 530 from user 140 references message 512 belonging to topic 1, which can be considered a historical message. Based on the message identifier of message 512, the stored information set of message dimensions associated with message 512 can be retrieved. The topic identifier indicated in this information set can be determined as the topic identifier of the topic to which message 512 belongs, also known as the target topic identifier. For example, the SessionID in the structure shown in Table 1 can be determined as the target topic identifier. Then, based on the target topic identifier, the stored context information of that topic can be retrieved, and the digital assistant's response message to message 530 can be retrieved according to this context information. Thus, the previously ended topic is reopened, and the previous context can be continued.

[0084] As mentioned above, multiple applications in the office suite 120 can access sub-sessions, meaning that sub-sessions with the digital assistant can be triggered through multiple applications. Additionally, in some embodiments, in response to an application triggering a sub-session, the server 130 can obtain a valid identifier for the sub-session window and initialize the sub-session based on that valid identifier. The valid identifier for the first sub-session window can be obtained in various ways. For example, it can first be determined whether the window identifier provided by the application is valid. If the window identifier is valid, it can be determined as the valid identifier for that window; conversely, if the window identifier is invalid, a new window identifier can be generated as the valid identifier for that window.

[0085] Figure 6 A flowchart illustrating a process 600 of an application accessing a sub- session is shown. As shown, at block 610, an application accessing a sub- session can be determined. At block 620, it is determined whether there is an existing sub-session window ID with the digital assistant, e.g., ChatModeID in Table 1. If there is an existing sub-session window ID, the process 600 proceeds to block 630. At block 630, it can be checked whether the existing sub-session window ID is valid. If it is valid, the process 600 proceeds to block 650. If it is not valid or if it is determined at block 620 that there is no sub-session window ID, the process 600 proceeds to block 640. At block 640, a sub-session window ID is obtained by initializing an interface. In turn, at block 650, a sub-session can be opened, and at block 660, the sub-session can be used, i.e., the user 140 and the digital assistant can interact in the sub-session. Thereafter, at block 370, the sub-session can be closed. The closing of the sub-session can be in response to the end of the sub-session scenario. For example, the user 140 can close the sub-session window, the user closes the tab of the application, the document is deleted in the case of a document application, the meeting is over in the case of a meeting application, etc. In such a case, a close interface can be called to close the sub-session. Alternatively or additionally, the closing of the sub-session can be in response to the sub-session not being updated for a preset duration of time. Figure 6

[0086] Figure 7 A flowchart illustrating a process 700 of information processing is shown. The process 700 can be implemented at the server 130. The process 700 is described below with reference to Figure 1 FIG. 7.

[0087] At block 710, the server 130 receives a first interaction message of a user with a digital assistant in a first sub-session, the first interaction message being from the user.

[0088] At block 720, the server 130 determines, based on a main session identification of a main session between the user and the digital assistant, a first information set associated with the main session.

[0089] At block 730, the server 130 determines, based on the first information set, a sub-session identification of the first sub-session.

[0090] At block 740, the server 130 determines, based on the sub-session identification, a first topic identification of a first topic to which the first interaction message belongs.

[0091] In some embodiments, determining the first topic identification of the first topic to which the first interaction message belongs comprises: querying, based on the sub-session identification, a second information set associated with the first sub-session; and in response to the querying of the second information set, determining, as the first topic identification, an identification of a current topic indicated in the second information set.

[0092] ​In some embodiments, the process 700 further includes: in response to the second information set not being queried, the server 130 generating the first topic identification and the second information set; and storing the second information set including the first topic identification, where the first topic identification is stored as an identification of the current topic of the first sub-conversation.

[0093] At block 750, the server 130 obtains stored context information of the first topic based on the first topic identification.

[0094] At block 760, the server 130 obtains a first reply message of the digital assistant to the first interaction message based on the context information.

[0095] In some embodiments, the process 700 further includes: the server 130 storing the first interaction information and the first reply message as part of the context information.

[0096] In some embodiments, the process 700 further includes: in response to the obtaining of the first reply message, the server 130 determining a third information set associated with the first topic based on the first topic identification; and determining a destination of the first reply message based on the third information set.

[0097] In some embodiments, the process 700 further includes: the server 130 generating a fourth information set associated with the first interaction message, the fourth information set including at least a message identification of the first interaction message, a sub-conversation identification, and the first topic identification; and generating a fifth information set associated with the first reply message, the fifth information set including at least a message identification of the first reply message, a sub-conversation identification, and the first topic identification.

[0098] In some embodiments, the process 700 further includes: in response to a second topic different from the first topic being opened, the server 130 receiving a second interaction message from the user; in response to the second interaction message referencing at least one of the first interaction message or the first reply message, querying an information set associated with the at least one interaction message based on a message identification of the at least one message; in response to determining the first topic identification from the queried information set, obtaining stored context information associated with the first topic identification based on the first topic identification; and generating a second reply message to the second interaction message based on the obtained context information.

[0099] In some embodiments, the process 700 further includes: in response to a triggering operation on the first sub-conversation by an application, the server 130 obtaining a valid identification of a window of the first sub-conversation; and initializing the first sub-conversation based on the valid identification of the window.

[0100] In some embodiments, obtaining the valid identifier of the window of the first sub-session comprises: determining whether the window identifier provided by the application is valid; in response to the window identifier being valid, determining the window identifier as the valid identifier of the window; and in response to the window identifier being invalid, generating a new window identifier as the valid identifier of the window.

[0101] Figure 8 Another flowchart of the process 800 of information processing is shown according to some embodiments. The process 800 can be implemented at the server 130. The process 800 is described below with reference to Figure 1 the server 130.

[0102] At block 810, the server 130 receives an interaction message of a user with a digital assistant in a session, the interaction message being from the user and referencing a historical message in the session.

[0103] At block 820, the server 130 obtains, based on a message identifier of the historical message, a set of information of stored message dimensions associated with the historical message.

[0104] At block 830, the server 130 determines, from the set of information of message dimensions, an indicated topic identifier as a target topic identifier of a topic to which the interaction message belongs.

[0105] At block 840, the server 130 obtains, based on the target topic identifier, stored context information of the topic.

[0106] At block 850, the server 130 obtains, based on the context information, a reply message of the digital assistant to the interaction message.

[0107] In some embodiments, the process 800 further comprises: the server 130 obtaining, based on a session identifier of the session, a set of information of session dimensions associated with the session; and updating an identifier of a current topic in the set of information of session dimensions to the target topic identifier.

[0108] Figure 9 A schematic structural block diagram of an apparatus 900 for information processing is shown according to certain embodiments of the present disclosure. The apparatus 900 can be implemented as or included in the server 130. Various modules / components in the apparatus 900 can be implemented by hardware, software, firmware, or any combination thereof.

[0109] The apparatus 900 includes a message receiving module 910 configured to receive a first interaction message of a user with a digital assistant in a first sub-conversation, the first interaction message being from the user. The apparatus 900 further includes a first information set determining module 920 configured to determine, based on a main-conversation identifier of a main-conversation between the user and the digital assistant, a first information set associated with the main-conversation. The apparatus 900 further includes a sub-conversation identifier determining module 930 configured to determine, based on the first information set, a sub-conversation identifier of the first sub-conversation. The apparatus 900 further includes a topic identifier determining module 940 configured to determine, based on the sub-conversation identifier, a first topic identifier of a first topic to which the first interaction message belongs. The apparatus 900 further includes a context information obtaining module 950 configured to obtain, based on the first topic identifier, stored context information of the first topic. The apparatus 900 further includes a reply message obtaining module 960 configured to obtain, based on the context information, a first reply message of the digital assistant to the first interaction message.

[0110] In some embodiments of the present disclosure, the apparatus 900 further includes that, in some embodiments, the topic identifier determining module 940 is further configured to: query, based on the sub-conversation identifier, a second information set associated with the first sub-conversation; and in response to querying the second information set, determine, as the first topic identifier, an identifier of a current topic indicated in the second information set.

[0111] In some embodiments, the topic identifier determining module 940 is further configured to: in response to not querying the second information set, generate the first topic identifier and the second information set; and store the second information set including the first topic identifier, where the first topic identifier is stored as an identifier of a current topic of the first sub-conversation.

[0112] In some embodiments, the apparatus 900 further includes a storing module configured to store the first interaction information and the first reply message as part of the context information.

[0113] In some embodiments, the apparatus 900 further includes a destination determining module configured to: in response to obtaining the first reply message, determine, based on the first topic identifier, a third information set associated with the first topic; and determine, based on the third information set, a destination of the first reply message.

[0114] In some embodiments, the apparatus 900 further includes: a fourth information set generating module configured to generate a fourth information set associated with the first interaction message, the fourth information set including at least a message identifier of the first interaction message, the sub-conversation identifier and the first topic identifier; and a fifth information set generating module configured to generate a fifth information set associated with the first reply message, the fifth information set including at least a message identifier of the first reply message, the sub-conversation identifier and the first topic identifier.

[0115] In some embodiments, the reply message obtaining module 960 is further configured to: after a second topic different from the first topic is opened, receive a second interaction message from the user; in response to the second interaction message referencing at least one message in the first interaction message or the first reply message, query the set of information associated with the at least one interaction message based on the message identifier of the at least one message; in response to determining the first topic identifier from the queried set of information, obtain the stored context information associated with the first topic identifier based on the first topic identifier; and generate a second reply message for the second interaction message based on the obtained context information.

[0116] In some embodiments, the apparatus 900 further includes an initialization module configured to, in response to the triggering operation on the first sub-session being applied, obtain a valid identifier of a window of the first sub-session; and initialize the first sub-session based on the valid identifier of the window.

[0117] In some embodiments, the initialization module is further configured to: determine whether a window identifier provided by the application is valid; in response to the window identifier being valid, determine the window identifier as the valid identifier of the window; and in response to the window identifier being invalid, generate a new window identifier as the valid identifier of the window.

[0118] Figure 10 A schematic structural block diagram of an apparatus 1000 for information processing according to certain embodiments of the present disclosure is shown. The apparatus 1300 can be implemented as or included in a server 130. The various modules / components in the apparatus 1000 can be implemented by hardware, software, firmware, or any combination thereof.

[0119] The apparatus 1000 includes a message receiving module 1010 configured to receive an interaction message of a user with a digital assistant in a session, the interaction message being from the user and referencing a historical message in the session. The apparatus 1000 further includes a set of information obtaining module 1020 configured to obtain a stored set of information of a message dimension associated with the historical message based on a message identifier of the historical message. The apparatus 1000 further includes a topic identifier determining module 1030 configured to determine a topic identifier indicated in the set of information of the message dimension as a target topic identifier of a topic to which the interaction message belongs. The apparatus 1000 further includes a context information obtaining module 1040 configured to obtain stored context information of the topic based on the target topic identifier. The apparatus 1000 further includes a reply message obtaining module 1050 configured to obtain a reply message of the digital assistant to the interaction message based on the context information.

[0120] In some embodiments, the apparatus 1000 further includes an updating module configured to obtain a set of information of session dimensions associated with the session based on the session identification of the session; and update an identification of a current topic in the set of information of session dimensions to the target topic identification.

[0121] Figure 11 A block diagram of an electronic device 1100 in which one or more embodiments of the disclosure can be implemented is shown. It should be understood that Figure 11 The electronic device 1100 shown is merely exemplary and should not be construed as limiting the scope of the embodiments described herein. Figure 11 The electronic device 1100 shown can be used to implement Figure 1 a terminal device 110 or a server 130.

[0122] As shown in Figure 11 The electronic device 1100 is in the form of a general electronic device. Components of the electronic device 1100 can include, but are not limited to, one or more processors or processing units 1110, a memory 1120, a storage device 1130, one or more communication units 1140, one or more input devices 1150, and one or more output devices 1160. The processing unit 1110 can be a real or virtual processor and is capable of executing various processing in accordance with programs stored in the memory 1120. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of the electronic device 1100.

[0123] The electronic device 1100 typically includes a number of computer storage media. Such media can be any available media that is accessible by the electronic device 1100 and includes both volatile and non-volatile media, removable and non-removable media. The memory 1120 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory), or some combination thereof. The storage device 1130 can be a removable or non-removable media and can include machine-readable media such as a flash drive, a magnetic disk drive, or any other media that can be used to store information and / or data and that can be accessed by the electronic device 1100.

[0124] The electronic device 1100 can further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown, the electronic device 1100 can further include a network adapter, a video display adapter, and the like. Figure 11As shown in FIG. 12, a disk drive 1211 and a disk drive 1212 can be provided for reading from or writing to a removable, non- volatile, magnetic media (e.g., a "floppy drive" or other magnetic media). In these cases, each drive can be connected to the bus 1205 by one or more data media interfaces. The memory 1210 can include a computer-readable product 1215 having one or more program modules configured to carry out the various methods or actions of the various embodiments of the present disclosure.

[0125] The communication unit 1140 enables communication through a communication medium with other electronic devices. Additionally, the functionality of the components of the electronic device 1100 can be implemented in a single computing cluster or a plurality of computer machines that are capable of communicating over a communication connection. As such, the electronic device 1100 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.

[0126] The input device 1150 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. The output device 1160 can be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 1100 can also communicate with one or more external devices (not shown) such as a storage device, a display device, etc., through the communication unit 1140, as needed, with one or more devices that enable a user to interact with the electronic device 1100, or with any devices (e.g., a network card, a modem, etc.) that enable the electronic device 1100 to communicate with one or more other electronic devices. Such communication can be carried out via an input / output (I / O) interface (not shown).

[0127] 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, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, where the computer-executable instructions are executed by a processor to implement the method described above.

[0128] Various aspects of the disclosure are now described with reference to the drawings. In general, the drawings described below are diagrammatic and schematic representations of actual or conceptual structures and processes, and are not limiting of the scope of the present disclosure. In the drawings, like reference numerals designate like structural elements throughout the various figures, wherein:

[0129] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0130] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0131] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0132] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An information processing method, comprising: Receive a first interaction message between the user and the digital assistant in a first sub-session, the first interaction message being from the user, the first sub-session including a conversation between the user and the digital assistant in an application other than a preset application; Based on the main session identifier of the main session between the user and the digital assistant, a first set of information associated with the main session is determined, wherein the main session includes the session between the user and the digital assistant in the preset application; Based on the first information set, determine the sub-session identifier of the first sub-session; Based on the sub-session identifier, determine the first topic identifier of the first topic to which the first interactive message belongs; Based on the first topic identifier, obtain the stored context information of the first topic; as well as Based on the context information, the digital assistant obtains its first response message to the first interaction message.

2. The method according to claim 1, wherein determining the first topic identifier of the first topic to which the first interaction message belongs includes: Based on the sub-session identifier, query the second information set associated with the first sub-session; as well as In response to finding the second information set, the identifier of the current topic indicated in the second information set is determined as the first topic identifier.

3. The method according to claim 2, further comprising: In response to the failure to find the second information set, the first topic identifier and the second information set are generated; as well as The storage includes a second set of information, which includes the first topic identifier, wherein the first topic identifier is stored as an identifier of the current topic of the first sub-session.

4. The method according to claim 1, further comprising: The first interaction message and the first response message are stored as part of the context information.

5. The method according to claim 1, further comprising: In response to the acquisition of the first reply message, a third set of information associated with the first topic is determined based on the first topic identifier; as well as Based on the third set of information, the destination of the first reply message is determined.

6. The method according to claim 1, further comprising: Generate a fourth information set associated with the first interaction message, the fourth information set including at least the message identifier of the first interaction message, the sub-session identifier, and the first topic identifier; as well as A fifth information set associated with the first reply message is generated, the fifth information set including at least the message identifier of the first reply message, the sub-session identifier, and the first topic identifier.

7. The method according to claim 6, further comprising: After a second topic different from the first topic is opened, a second interactive message is received from the user; In response to the second interaction message referencing at least one of the first interaction message or the first reply message, a set of information associated with the at least one message is queried based on the message identifier of the at least one message; In response to determining the first topic identifier from the retrieved information set, and based on the first topic identifier, obtaining the stored context information associated with the first topic identifier; as well as Based on the acquired context information, a second response message is generated for the second interaction message.

8. The method according to claim 1, further comprising: In response to a triggering operation on the first sub-session via the other application, a valid identifier of the window of the first sub-session is obtained; as well as The first sub-session is initialized based on the valid identifier of the window.

9. The method according to claim 8, wherein obtaining the valid identifier of the window of the first sub-session includes: Determine whether the window identifier provided by the other application is valid; In response to the window identifier being valid, the window identifier is determined as a valid identifier for the window; as well as In response to the invalidation of the window identifier, a new window identifier is generated as the valid identifier of the window.

10. An information processing method, comprising: Receive interaction messages between the user and the digital assistant in a conversation, the interaction messages being from the user and referencing historical messages in the conversation; Based on the message identifier of the historical message, obtain the information set of the stored message dimensions associated with the historical message; The topic identifier indicated in the information set of the message dimension is determined as the target topic identifier of the topic to which the interactive message belongs; Based on the target topic identifier, obtain the stored context information of the topic; as well as Based on the context information, obtain the digital assistant's response message to the interaction message.

11. The method of claim 10, further comprising: Based on the session identifier of the session, obtain the information set of the session dimension associated with the session; as well as Update the identifier of the current topic in the information set of the conversation dimension to the identifier of the target topic.

12. An apparatus for information processing, comprising: The message receiving module is configured to receive a first interaction message between a user and a digital assistant in a first sub-session, the first interaction message being from the user, and the first sub-session including a conversation between the user and the digital assistant in an application other than a preset application; The first information set determination module is configured to determine a first information set associated with the main session based on the main session identifier of the main session between the user and the digital assistant, wherein the main session includes the session between the user and the digital assistant in the preset application; The sub-session identifier determination module is configured to determine the sub-session identifier of the first sub-session based on the first information set; The topic identifier determination module is configured to determine the first topic identifier of the first topic to which the first interaction message belongs based on the sub-session identifier; The context information acquisition module is configured to acquire the stored context information of the first topic based on the first topic identifier; as well as The response message acquisition module is configured to acquire the first response message from the digital assistant to the first interaction message based on the context information.

13. An apparatus for information processing, comprising: The message receiving module is configured to receive interaction messages between a user and a digital assistant in a conversation, the interaction messages being from the user and referencing historical messages in the conversation; The information set acquisition module is configured to acquire the information set of the stored message dimensions associated with the historical message based on the message identifier of the historical message; The topic identifier determination module is configured to determine the topic identifier indicated in the information set of the message dimension as the target topic identifier of the topic to which the interactive message belongs; The context information acquisition module is configured to acquire the stored context information of the topic based on the target topic identifier; as well as The response message acquisition module is configured to acquire the digital assistant's response message to the interaction message based on the context information.

14. An electronic device, comprising: At least one processing unit; as well as At least one memory is coupled to the at least one processing unit and stores 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 9 or any one of claims 10 to 11 when executed by the at least one processing unit.

15. 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 9 or any one of claims 10 to 11.

Images