Method and apparatus for information processing, and device and storage medium

Abstract

In the embodiments of the present disclosure, provided are a method and apparatus for information processing, and a device and a storage medium. The method comprises: on the basis of an interaction event between a target object and at least one service component, generating historical interaction information for the interaction event, wherein the historical interaction information at least comprises a knowledge element, and the knowledge element is used for describing a service object associated with the interaction event; and providing the historical interaction information for interaction between the target object and a digital assistant. Thus, by using a knowledge element to describe a service object involved in an interaction event, the embodiments of the present disclosure can support a digital assistant in providing richer interaction capabilities.

Description

Method, device, equipment and storage medium for information processing

[0001] This application claims priority to the Chinese invention patent application with application number 202311285164.9 filed on September 28, 2023 and titled “Methods, devices, equipment and storage media for information processing”, the entire contents of which are incorporated by reference into this application. Technical Field

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

[0003] With the rapid development of Internet technology, the Internet has become an important platform for people to obtain and share content. Users can access the Internet through terminal devices to enjoy various Internet services.

[0004] In addition, Internet platforms can also provide users with various types of information processing capabilities. How to improve the accuracy of such information processing has become a focus of attention.

[0005] Summary of the Invention

[0006] In a first aspect of the present disclosure, a method for information processing is provided. The method comprises: generating historical interaction information for an interaction event between a target object and at least one business component, the historical interaction information comprising at least a knowledge element describing a business object associated with the interaction event; and providing the historical interaction information for interaction between the target object and a digital assistant.

[0007] In a second aspect of the present disclosure, a device for information processing is provided. The device includes: a generation module configured to generate historical interaction information for an interaction event between a target object and at least one business component based on the interaction event, the historical interaction information including at least a knowledge element, the knowledge element being used to describe the business object associated with the interaction event; and a providing module configured to provide the historical interaction information for interaction between the target object and a digital assistant.

[0008] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0009] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0010] It should be understood that the content described in this summary section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0012] FIG1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;

[0013] FIG2 illustrates an example system architecture according to some embodiments of the present disclosure;

[0014] FIG3 illustrates an example log entry according to some embodiments of the present disclosure;

[0015] FIG4 shows a schematic diagram of knowledge elements for generating a document according to some embodiments of the present disclosure;

[0016] FIG5 shows a flowchart of a method for information processing according to some embodiments of the present disclosure;

[0017] FIG6 shows a block diagram of an apparatus for information processing according to some embodiments of the present disclosure; and

[0018] FIG7 shows a block diagram of a device capable of implementing various embodiments of the present disclosure. DETAILED DESCRIPTION

[0019] It is understood that before using the technical solutions disclosed in each embodiment of this disclosure, the type, scope of use, and usage scenarios of the information involved in this disclosure should be informed to relevant users in an appropriate manner in accordance with relevant laws and regulations, and authorization from relevant users should be obtained. The relevant users can include any type of right holders, such as individuals, enterprises, and groups.

[0020] For example, in response to receiving a user's active request, a prompt message is sent to the relevant user to clearly inform the relevant user that the operation requested by the relevant user will require the acquisition and use of the relevant user's information. In this way, the relevant user can independently choose whether to provide information to the electronic device, application, server, storage medium, or other software or hardware that performs the operation of the technical solution of the present disclosure based on the prompt message.

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

[0022] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0023] It is understandable that when adopting this technical solution, the data involved (including but not limited to the data itself, the acquisition, use, storage, and transmission of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0024] As used herein, the term "in response to" refers to a state in which a corresponding event occurs or a condition is satisfied. It will be understood that the timing of executing a subsequent action executed in response to the event or condition is not necessarily strongly correlated with the time when the event occurs or the condition is satisfied. For example, in some cases, a subsequent action may be executed immediately upon the occurrence of the event or the satisfaction of the condition; in other cases, the subsequent action may be executed some time after the occurrence of the event or the satisfaction of the condition.

[0025] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

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

[0027] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0028] As used herein, the term "model" can learn the association between corresponding inputs and outputs from training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation and use of the model can be based on technologies permitted by laws and regulations such as machine learning, referred to as available technologies. For example, deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multiple layers of processing units. In this article, "model" may also be referred to as "machine learning model", "machine learning network" or "network", and these terms are used interchangeably in this article. A model may also include different types of processing units or networks.

[0029] As briefly mentioned above, people can already use various types of information processing tools to improve the efficiency of information processing. For example, some digital assistants can generate corresponding responses based on conversational interactions with users (e.g., text or voice).

[0030] However, such information processing is usually a generalized capability that provides similar information processing capabilities to many users. However, due to the different interaction habits and needs of different users, it may be difficult for users to obtain the expected information processing results.

[0031] Embodiments of the present disclosure provide a solution for information processing. Specifically, historical interaction information for an interaction event can be generated based on an interaction event between a target object (e.g., a user or organization) and at least one business component. The historical interaction information includes at least a knowledge element, which is used to describe the business object associated with the interaction event. Furthermore, the historical interaction information can be provided for interaction between the target object and the digital assistant.

[0032] Therefore, the embodiments of the present disclosure can use knowledge elements to describe the business objects involved in interactive events, thereby supporting digital assistants to provide richer interactive capabilities.

[0033] Example embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0034] Sample Environment

[0035] FIG1 illustrates a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in FIG1 , in environment 100, a terminal device 110 can be utilized to provide a digital assistant 102 to a target object 150. Such a target object may include a user or an organization, where an organization may be a business, group, department, or the like.

[0036] Exemplarily, such a digital assistant 102 may also be referred to as a digital assistant, or a digital robot. It should be understood that although the digital assistant 102 is shown as being included in the terminal device 110 in FIG1 , part of the processing capabilities of the digital assistant 102 may also be at least partially based on the server 120 . For example, the front-end portion of the digital assistant 102 (e.g., the portion for presentation) may be included in the terminal device 110, but the back-end portion of the digital assistant 102 (e.g., the portion for information processing) may be included in the server 120.

[0037] In some examples, the digital assistant 102 can be, for example, a digital assistant that assists the target object 150, such as an office worker, or can be any other appropriate entity. The digital assistant 102 can also run independently or be integrated into a specific application.

[0038] In some embodiments, the digital assistant 102 can be enabled, for example, called or awakened, by an appropriate means (e.g., a shortcut key, a button, or voice). If the digital assistant 102 is active, the terminal device 110 can present an interface 104 associated with the digital assistant 102. The interface 104 can be in the style of a conversational user interface (also referred to as a conversation interface or conversation window), or it can be any other appropriate interface form. As will be described in detail below, such an interface 104 can also include interface elements for information interaction, such as a message input box, a message list, a message bubble, and so on. Through the interface 104, the digital assistant 102 can obtain information input by the target object 150 (also referred to as first information).

[0039] Such input information may include, for example, any appropriate type of message, such as a text message, a picture message, a voice message, a form message, a link message, other appropriate types of messages, and the like.

[0040] Furthermore, the server 120 may allow the target object 150 to interact with the digital assistant 102 to obtain information generated by the digital assistant 102. Alternatively, as will be described in detail below, with the authorization of the target object 150, the information generated by the digital assistant 102 may also be based on historical interactions between the target object 150 and at least one business component 115.

[0041] Such business components may include components that can provide appropriate types of business services for the target object 150. Examples include, but are not limited to, office components and tool components. In some embodiments, such business components may be installed on the same terminal device 110. Alternatively or additionally, such business components may be installed on other terminal devices or provided as cloud services.

[0042] In some embodiments, such business components 115 may include multiple office components in an office suite. An office suite may be a set of office components developed to improve office efficiency, such as office components for creating and editing documents, office components for creating and editing tables, office components for drawing, and the like.

[0043] In some embodiments, the multiple office components include multiple items of the following: a chat component, a document component, an audio and video conferencing component, an email component, a calendar component, a schedule component, a task component, an Objectives and Key Results (OKR) component, and / or appropriate office components that are currently available or may be developed in the future.

[0044] In some embodiments, the digital assistant 102 may be a separate application from the business component 115. Alternatively, the digital assistant 102 may be a function or component appropriately integrated into the business component 115.

[0045] In some embodiments, the historical interaction information 130 may be maintained on appropriate electronic devices as needed, such as the terminal device 110, the server 120, and / or other appropriate electronic devices. The historical interaction information 130 may include, for example, both interaction information stored on the terminal device 110 and interaction information uploaded to the server 120.

[0046] As will be described in detail below, historical interaction information 130 may be provided for interaction between the digital assistant 102 and the target object 150. As an example, the digital assistant 102 may obtain input information of the target object 150, and the digital assistant 102 or the server 120 may generate corresponding information (also referred to as third information) based on the input information and the historical interaction information 130. The historical interaction information 130 may, for example, indicate a historical interaction process between the target object 150 and at least one business component 115.

[0047] Furthermore, the server 120 or the digital assistant 102 may send the generated third information to the target processing entity 140. Furthermore, the server 120 or the digital assistant 102 may generate corresponding information (also referred to as second information) based on the information returned by the target processing entity 140 (i.e., the processing result of the third information). Such second information may be presented to the target object 150 via the interface 104 corresponding to the digital assistant 102, for example.

[0048] The target processing entity 140 may be a processing entity based on appropriate information processing technology, and may implement one or more functions such as text generation, image generation, summarization, encoding, translation, chatbot, etc. The target processing entity 140 may also be any other appropriate entity form.

[0049] In some embodiments, the terminal device 110 communicates with the server 120 to enable the provision of services to the digital assistant 102. The terminal device 110 can be any type of mobile terminal, fixed terminal or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a gaming device or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some embodiments, the terminal device 110 can also support any type of interface for the target object 150 (such as a "wearable" circuit, etc.). The server 120 can be various types of computing systems / servers that can provide computing capabilities, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, and the like.

[0050] Although only one server 120 is shown in FIG1 , the environment 100 may include multiple servers 120. For example, the historical interaction information 130 may be stored locally or in a second server 120 as needed and with relevant user authorization, and the target processing entity 140 may be run on a third server 120. It should be understood that this is merely an exemplary description and does not imply any limitation on the scope of the present disclosure.

[0051] It should be understood that the structure and functionality of environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure.

[0052] The generation and management process of the historical interaction information 130 will be described below with reference to FIG. 2 , which shows an example system architecture 200 according to an embodiment of the present disclosure.

[0053] As shown in FIG. 2 , when target object 150 interacts with business component 115 , business component 115 may generate log records and send the log records to logging module 210 .

[0054] Furthermore, the recording module 210 can generate corresponding record entries based on the received log records and build a record library. In some embodiments, such record entries can include knowledge elements (Knowledge) to describe the business objects corresponding to the historical interaction events. In some embodiments, the record library can be maintained in an appropriate electronic device, which can be stored, for example, at the terminal device 110 or at the server 120.

[0055] In some embodiments, such business objects may include business objects generated, edited, referenced, shared, and the like by the target object 150 during its interaction with the business component 115. For example, if the business component 115 is a document component, a historical interaction event may include a creation event of a specific document in the document component by the target object 150. Accordingly, the business object corresponding to the document creation event is the specific document.

[0056] In some embodiments, a knowledge element may be a natural language description of the business object, which is intended to abstract and / or compress the content of the business object. For example, taking a document object as an example of a business object, the knowledge element may be used to describe the subject, completion status, audience, language, and expression style of the document object.

[0057] It should be understood that, depending on the type of business object, different dimensions of information can be selected to generate knowledge elements for describing the business object. For example, taking a conversation as an example business object, knowledge elements can be used to describe the type of conversation (e.g., whether it is a one-on-one chat), the overview of the conversation, etc.

[0058] Therefore, by maintaining knowledge elements in record entries, embodiments of the present disclosure can describe or characterize the business objects involved in the corresponding historical interaction events through limited content length.

[0059] In some embodiments, the record entry may further include a time element for indicating the time of occurrence of the historical interaction event. For example, continuing to use the example of creating a document as a historical interaction event, such a time element may, for example, indicate the creation time of the document.

[0060] In some other embodiments, the record entry may further include an action element for indicating the 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, for example, indicate that the type of the historical interaction event is "create".

[0061] In some embodiments, the record entry may further include a payload element for indexing a business object corresponding to the corresponding 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 for indexing the document.

[0062] Therefore, in some scenarios, after the target object 150 interacts with the business component 115, the recording module 210 can generate a corresponding record entry. Such a record entry can be represented as {time element, action element, knowledge element, payload element}, for example, to describe the historical interaction event from multiple preset dimensions.

[0063] FIG3 illustrates example record entries according to some embodiments of the present disclosure. As shown in FIG3 , the record library may maintain, for example, three record entries corresponding to three historical interaction events between the target object 150 and the document component. Such record entries may respectively indicate the "time elements" 305, 320, and 335 corresponding to the three interaction events; the action elements 310, 325, and 340 corresponding to the three interaction events; the payload elements 315, 330, and 345 corresponding to the three interaction events; and the knowledge element 355 of the business object (i.e., document 350) corresponding to the three interaction events.

[0064] As discussed above, knowledge elements are intended to describe and summarize the content of a business object, and their core capability is the abstraction and compression of content information. In some embodiments, the recording module 210 can generate a first portion of a knowledge element based on the metadata of the business object so that the knowledge element can indicate the metadata of the business object.

[0065] Taking a document type object (also referred to as a document) as an example, a knowledge element of a document may be used to indicate one or more metadata of the document.

[0066] In some embodiments, the knowledge element of a document may indicate identification information of the document. Such identification information may include, for example, the title of the document, for example, "A Document".

[0067] In some embodiments, a document's knowledge element may indicate user information for the document, where the user information indicates at least one user associated with the document. For example, a document's knowledge element may indicate that the document's creators include user X and user Y. As another example, a document's knowledge element may also indicate that the document's editors include N users, with the document's primary editorial contributors being user X and user Y.

[0068] In some embodiments, the knowledge element of a document may indicate time information of the document, wherein the time information indicates the occurrence time of a historical event associated with the document. For example, the knowledge element of a document may indicate the creation time of the document.

[0069] In some embodiments, the knowledge element of a document may indicate the spread information of the document, wherein the spread information indicates the degree of spread of the document. For example, the knowledge element of a document may indicate the number of times the document has been read or shared.

[0070] In some embodiments, the knowledge element of a document may indicate permission information of the document, wherein the permission information indicates a permission management policy of a document type object. For example, the knowledge element of a document may indicate the confidentiality level of the document within an organization.

[0071] In some embodiments, the knowledge elements of a document may indicate the business component to which the document belongs. For example, the knowledge elements of a document may indicate that the document is related to a specific business component.

[0072] Taking a session type object (also referred to as a session) as an example of a business object, the knowledge element of the session may indicate one or more metadata of the session.

[0073] In some embodiments, the knowledge element of a conversation may indicate the conversation type of the conversation, which may include topic conversation, internal conversation, external conversation, public conversation, private conversation, single chat conversation, group chat conversation, etc.

[0074] By using knowledge elements to indicate metadata of business objects, embodiments of the present disclosure can more conveniently locate business objects to be matched.

[0075] In some embodiments, the recording module 210 may further generate a second portion of the knowledge element based on the content of the business object, so that the knowledge element can describe the content of the business object.

[0076] Taking a document type object (also referred to as a document) as an example, the knowledge elements of a document can be used to describe various aspects of the content of the document.

[0077] In some embodiments, a knowledge element of a document can be used to indicate the completion status of the content of the document. For example, a knowledge element can indicate that the document is completed within a specific time period. Alternatively, a knowledge element can indicate that the document has not yet been completed.

[0078] In some embodiments, the knowledge elements of a document can be used to indicate an overview of the content of the document. For example, such an overview can be used to summarize the core themes or viewpoints of the content of the document. It should be understood that any appropriate method can be used to generate an overview of the content of the document.

[0079] In some embodiments, the knowledge element of a document may be used to indicate the type of the content of the document. For example, such a type may be used to indicate whether the document is a product requirements document or a project schedule management document.

[0080] In some embodiments, the knowledge elements of a document may be used to indicate keywords of the content of the document. For example, one or more representative keywords in the content of the document may be extracted based on an appropriate keyword determination method.

[0081] In some embodiments, the knowledge elements of a document may also be used to indicate the target users of the content of the document. Such target users may include, for example, the audience of the document.

[0082] In some embodiments, the knowledge elements of a document may be used to indicate style information of the content of the document. Such style information may be used to describe the language or expression style of the document content.

[0083] In this way, knowledge elements can be used to compress and refine the content of a document, thereby supporting the digital assistant to use the knowledge elements of the document for corresponding processing and response without transmitting the original content of the document.

[0084] In some embodiments, the knowledge elements of a document may also be used to indicate an overview of each of the multiple segments of the document. Figure 4 shows a schematic diagram of generating knowledge elements of a document according to some embodiments of the present disclosure.

[0085] As shown in FIG4 , document 410 may be divided into multiple segments 420. In some embodiments, recording module 210 may, for example, divide document 410 into multiple segments 420 based on the structure of the document. For example, recording module 210 may divide document 410 into multiple segments 420 corresponding to different sections based on the section information of the document.

[0086] Alternatively, the recording module 210 may also split the document based on other appropriate information, such as but not limited to: editor, editing time, etc.

[0087] Furthermore, the recording module 210 may generate summaries corresponding to the plurality of segments 420, for example, segment summary 430, segment summary 440, segment summary 450, and segment summary 460. The recording module 210 may maintain the generated segment summaries 430 to 460 in the knowledge element of the document. It should be understood that, compared to the overall summary of the content of the document, the summary of each segment will have more fine-grained information, thereby enabling the digital assistant to more accurately determine whether it is relevant to the received input information.

[0088] In some embodiments, when generating the segment summaries for each segment, the recording module 210 may also consider order information between the segments. This order information is intended to indicate the relevance of the content of each segment within the document. For example, the segment summary corresponding to the "Introduction" section may indicate that this section of the summary corresponds to the "Introduction" section of the document.

[0089] In some embodiments, the recording module 210 can also use reference information to generate a segment overview of each segment. Such reference information can be used to assist in understanding the content of the document. For example, some documents may contain some non-common words. In the absence of explanations for non-common words, it may be difficult to accurately generate an overview of the document. Thus, the recording module 210 can use knowledge elements to indicate the definitions of these non-common words, thereby improving the accuracy of the digital assistant 102 in processing information. For example, the digital assistant can respond more accurately to requests or inputs containing non-common words.

[0090] By splitting a document into multiple document segments, the embodiments of the present disclosure can increase the amount of information contained in the knowledge elements of the document, thereby supporting digital assistants to improve the accuracy of information processing.

[0091] Taking a session type object (also referred to as a session) as an example, the knowledge element of the session can be used to describe the content of the session.

[0092] In some embodiments, the knowledge element of a session may be used to indicate a functional description of the session. For example, the knowledge element of a session may indicate that the session corresponds to a product requirement discussion group or a product feature feedback group.

[0093] In some embodiments, the knowledge element of a conversation can also be used to indicate an overview of the content of messages in the conversation. For example, the knowledge element of a conversation can indicate the topic discussed by the messages in the conversation, for example, "the progress of project X was discussed."

[0094] In some embodiments, multiple messages in a conversation may be aggregated into multiple message sets, and the knowledge element of the conversation indicates an overview of each message set in the multiple message sets.

[0095] In some embodiments, the multiple message sets are aggregated based on the time of the multiple messages in the conversation type object. Alternatively, the multiple message sets are aggregated based on the topics to which the multiple messages in the conversation belong. For example, the recording module 210 may also split the messages in the conversation into multiple message sets based on factors such as the speaker, topic, and message time, and generate a content summary for each message set.

[0096] The above describes the process of generating knowledge elements by using documents and sessions as examples. It should be understood that knowledge elements of other types of business objects can be generated in a similar manner to indicate metadata and / or content of the corresponding business objects.

[0097] Furthermore, based on the above, knowledge elements can be organized according to a preset content structure to construct structured information. Specifically, a knowledge element can have a content structure corresponding to a type of business object (eg, a document object, a message object, etc.).

[0098] By utilizing structured knowledge elements to maintain multi-dimensional information of business objects, the embodiments of the present disclosure can facilitate the search and location of corresponding business objects, and can also compress document content, thereby reducing the management and maintenance costs of record entries.

[0099] In some embodiments, as discussed above, the log entry may also include an action element to indicate the event type of the interactivity event.

[0100] In some embodiments, the event type may include a production event associated with a business object. Such a production event may correspond to a production process such as generation or editing of the business object.

[0101] Alternatively or additionally, the event type may be a consumption event associated with a business object. Such a consumption event may correspond to a consumption process such as reading, subscribing, or collecting the business object.

[0102] Alternatively or additionally, the event type may be a circulation event associated with a business object, such as a circulation process of the business object being shared or presented in a search scenario.

[0103] Alternatively or additionally, the event type may be a management event associated with a business object. Such a management event may correspond to a management process such as permission setting of the business object.

[0104] Alternatively or additionally, the event type may be an interactive event associated with a business object. Such an interactive event may correspond to an interactive process such as a reference or reply to a business object.

[0105] Taking a document type object as an example of a business object, the event type of an interactive event for a document may include, for example, a production event associated with the document. Such production events may include, but are not limited to, a document creation event, an editing event, and the like.

[0106] Additionally or alternatively, the event type of the interaction event for a document may include, for example, a consumption event associated with the document. Such consumption events may include, but are not limited to: reading a document, commenting on a document, liking a document, adding a document to a favorite, printing a document, moving a document, downloading a document, subscribing to a document, adding a document shortcut, etc.

[0107] Additionally or alternatively, the event type of the interaction event for a document may include, for example, a circulation event associated with the document. Such circulation events may include, but are not limited to: a document being shared to a conversation, a document being shared to a meeting, a document being attached to a schedule, a document having a collaborator added, a document being searched and clicked, a document being searched and presented, etc.

[0108] Additionally or alternatively, the event type of the interaction event for the document may include, for example, a management event associated with the document. Such management events may include, but are not limited to, document permission management, such as confidentiality settings, collaborator management, and sharing permission settings.

[0109] Taking a message type object (also referred to as a message) as an example of a business object, the event type of an interactive event for a message may include, for example, a production event associated with the message. Such a production event may include, for example, but is not limited to: editing a message draft, sending a message, etc.

[0110] Additionally or alternatively, the event type of the interaction event for a message may include, for example, a consumption event associated with the message. Such consumption events may include, but are not limited to: reading a message, marking a message, adding a favorite message, pinning a message, adding a task based on a message, translating a message, deleting a message, etc.

[0111] Additionally or alternatively, the event type of the interactive event for the message may include, for example, an interactive event associated with the message. Such interactive events may include, but are not limited to: replying to a message with an emoticon, quoting a message, a conversation topic, forwarding a message (single forwarding, combined forwarding), etc.

[0112] Additionally or alternatively, the event type of an interactive event for a message may include, for example, a circulation event associated with the message. Such circulation events may include, but are not limited to, sharing of message content. Unlike message forwarding, such content sharing may, for example, be performed by generating a link to the message content.

[0113] In this way, embodiments of the present disclosure can use preset event types to accurately characterize the types of interaction events between target object 150 and business component 102. In addition, different preset event types can be set for different types of business objects, thereby improving the accuracy of action element expression.

[0114] It should be understood that the record entry may also include other appropriate elements to describe other appropriate dimensions of the corresponding historical interaction event.

[0115] Based on this approach, the record module 210 can support the interaction between the target object 150 and the digital assistant 102 by maintaining a set of record entries in a record library. Such a record library can also be similar to the "memory information" of the digital assistant, thereby helping the digital assistant improve the quality of the generated response content.

[0116] In some embodiments, considering that the size of the corresponding record library will become larger as the target object 150 interacts more and more with the business component 115, the record module 210 may also perform compression processing on the record entries in order to more effectively manage the historical interaction information.

[0117] For example, the recording module 210 may periodically compress the record entries in the record library to compress multiple record entries into one compressed record entry. For example, the recording module 210 may perform compression processing on the record entries based on the occurrence time of the historical interaction event.

[0118] In some embodiments, when multiple historical interaction events have occurred for more than a threshold period of time (for example, one month), the recording module 210 can remove the record entries of the multiple historical interaction events from the record library and generate corresponding record compression entries.

[0119] Exemplarily, the recording module 210 may identify a group of record entries to be compressed from the record library, where such a group of record entries to be compressed may correspond to associated interaction events (eg, associated with the same business object) whose occurrence date has exceeded a threshold duration.

[0120] For example, target object 150 may have created document A, edited document A, and shared document A within a week one month ago. Accordingly, the record library may have previously maintained three record entries corresponding to these three historical interaction events. Furthermore, upon determining that all three historical interaction events occurred one month ago, record module 210 may compress the three record entries into a single compressed record entry.

[0121] In the process of compressing multiple record entries into a single compressed record entry, the recording module 210 may, for example, only retain important information in the multiple record entries, thereby reducing storage and management overhead of the record entries.

[0122] In some embodiments, the method of compressing record entries may also include, for example, retaining some of the record entries to be compressed. Continuing with the example of creating document A, editing document A, and sharing document A, the recording module 210 may, for example, retain only the record entry corresponding to "editing document A," which may also be referred to as a compressed record entry.

[0123] This recording method can also be similar to the way human memory is managed. That is, for historical events that are older, the recording module can maintain relatively vague recording information. On the contrary, for historical events that are more recent, the recording module can maintain more accurate recording information.

[0124] In some embodiments, the recording module 210 may utilize a compression model to compress the record entries. Specifically, the recording module 210 may provide the record model with multiple record entries to be compressed to obtain compressed record entries corresponding to the multiple record entries to be compressed. Such a compression model may be implemented using an appropriate machine learning model.

[0125] In some examples, the compression model may be the target processing entity 140 discussed with reference to FIG1 . That is, the recording module 210 may provide the target processing entity 140 with a guide word for instructing the target processing entity 140 to perform compression, along with a plurality of record entries to be compressed, to obtain compressed record entries. For example, such a guide word may be "Please select the three most representative record entries from the following multiple record entries" or "Please compress the following multiple record entries into a single entry."

[0126] Based on this approach, the recording module 210 may, for example, periodically compress the record entries to reduce the management and maintenance costs of the record entries.

[0127] In some embodiments, with the knowledge and authorization of the target object 150, the recording module 210 may further reflect the recorded entries to generate interaction pattern information associated with the target object 150. Such interaction pattern information may be used to indicate interaction characteristics corresponding to at least one historical interaction event.

[0128] For example, the recording module 210 may extract common features based on multiple record entries to reflect the interaction characteristics associated with the target object 150. For example, based on multiple historical record entries corresponding to the target object 210 writing a weekly report, the recording module 210 may extract corresponding interaction characteristics such as "writing a weekly report every Monday afternoon" or "checking meeting minutes before writing a weekly report."

[0129] In some embodiments, the recording module 210 can utilize a specific processing model to extract interaction pattern information. Specifically, the recording module 210 can, for example, provide multiple record entries to be extracted to the processing model to obtain one or more pieces of interaction pattern information corresponding to the multiple record entries to be extracted. Such a processing model can be implemented using an appropriate machine learning model.

[0130] In some examples, the processing model may be the target processing entity 140 discussed with reference to Figure 1. That is, the recording module 210 may obtain refined interaction pattern information by providing the target processing entity 140 with a guide word for guiding the target processing entity 140 to perform interaction feature extraction and a plurality of record entries to be extracted.

[0131] Based on the above method, the recording module 210 can, for example, maintain one or more of the record entries corresponding to historical interaction events, the record compression entries obtained by compressing the record entries, and / or the interaction pattern information obtained by refining the record entries for generating the second information.

[0132] In some embodiments, as discussed with reference to FIG. 1 , server 120 may utilize target processing entity 140 to generate the second information.

[0133] Specifically, server 120 may process the first information to generate third information based on historical interaction information 130. Further, server 120 may provide the third information to target processing entity 140, where target processing entity 140 is different from digital assistant 102. Additionally, server 120 may generate second information based on a result of processing the third information by target processing entity 140.

[0134] In some embodiments, the target processing entity 140 may include a target model, such as a target language model. Accordingly, the third information may include, for example, input information for the target model. In some scenarios, such third information may also be referred to as a prompt word, a guide word, or a prompt to the target model. It should be understood that, depending on the needs of the actual scenario, the target processing entity 140 may also include, for example, other appropriate models.

[0135] To obtain more accurate and effective third information, server 120 may process the first information based on a set of record entries included in historical interaction information 130. In some embodiments, after digital assistant 102 receives the first information (also referred to as query information) input by target object 150, server 130 may determine at least one record entry associated with the first information from the set of record entries maintained by record module 210.

[0136] It should be understood that any appropriate technique can be used to determine at least one record entry associated with the first information. For example, server 120 can perform a semantic analysis of the first information and determine, from the set of record entries, at least one record entry associated with the semantics of the first information. Alternatively, server 120 can also determine, from a record library, at least one record entry associated with the semantics of the first information based on, for example, a keyword search or match.

[0137] As an example, server 120 may determine at least one associated record entry based on similarity between the record entry and the first information. Specifically, server 120 may determine a set of description vectors corresponding to a set of record entries maintained in a record repository and a target description vector corresponding to the received first information. Furthermore, server 120 may determine at least one record entry associated with the first information from the set of record entries based on the target description vector and the set of description vectors corresponding to the set of record entries.

[0138] As an example, the server 120 may determine, from the group of record entries, a record entry whose angle between its corresponding description vector and the target description item vector is smaller than a threshold, as the at least one record entry associated with the first information.

[0139] For example, if the first information input in the target object is "Please write this week's report based on the style of document A," the record entries determined by the server 120 may include one or more record entries associated with the business object "document A," such as the record entries shown in FIG3 .

[0140] Accordingly, the server 120 may also generate third information to be provided to the target processing entity 140 based on the first information and the associated at least one record entry. For example, the server 120 may retain the first information and then add additional information corresponding to the associated at least one record entry to generate the third information. For example, such additional information may be generated based on the associated at least one record entry.

[0141] For example, the server 120 may provide all or part of the knowledge element of "Document A" as the third information to the target processing entity 140. For example, the server 120 may provide the portion of "Document's Language Expression Form" in the knowledge element 355 that represents the style information of "Document A" to the target processing entity 140, so that the target processing entity 140 can respond to the first information based on the style information.

[0142] As another example, the server 120 may also rewrite the first information based on at least one associated record entry, for example, expand the first information, so that the first information can more accurately reflect the needs of the target object 150 .

[0143] In some embodiments, the server 120 may further process the first information based on a set of compressed record entries included in the historical interaction information 130 to generate the second information. For example, similar to the process of determining the associated record entry, the server 120 may determine at least one compressed record entry associated with the first information from the set of compressed record entries maintained by the recording module 210.

[0144] Furthermore, the server 120 may utilize the determined at least one record compression entry and the first information to generate third information to be provided to the target processing entity 140. For example, the server 120 may retain the first information and then add additional information corresponding to the associated at least one record compression entry to generate the third information. For example, such additional information may be generated based on the associated at least one record compression entry.

[0145] As another example, the server 120 may also rewrite the first information based on at least one associated record compression entry, for example, expand the first information, so that the first information can more accurately reflect the needs of the target object 150 .

[0146] In some embodiments, the server 120 may further process the first information to generate the second information based on the interaction pattern information included in the historical interaction information 130. For example, the server 120 may determine at least one item of interaction pattern information associated with the first information.

[0147] Furthermore, the server 120 may utilize the determined at least one item of interaction mode information and the first information to generate third information to be provided to the target processing entity 140. For example, the server 120 may retain the first information and then add additional information corresponding to the at least one item of associated interaction mode information to generate the third information. For example, such additional information may be generated based on the at least one item of associated interaction mode information.

[0148] As another example, the server 120 may also rewrite the first information based on at least one associated interaction mode information, for example, expand the first information, so that the first information can more accurately reflect the needs of the target object 150 .

[0149] Based on this approach, the embodiment of the present disclosure can generate third information that better meets the interaction needs of the target object 150 based on the historical interaction information 130, and can improve the accuracy of information processing while the user maintains his or her personal interaction habits.

[0150] Furthermore, the terminal device 110 may also obtain second information generated based on the first information, and provide the second information to the target object 150 as a response to the first information.

[0151] The above discusses an example process in which the digital assistant 102 generates second information based on the first information input by the target object 150. Based on the above method, the embodiments of the present disclosure can improve the accuracy of information processing, so that the generated second information is more in line with the interaction habits of the target object 150 and its needs for interaction results.

[0152] Furthermore, through this approach, embodiments of the present disclosure can also support a richer range of user requests. For example, target object 150 can input the first message "Please refer to my last weekly report to write a weekly report for Project X" to digital assistant 102. Accordingly, digital assistant 102 can generate a draft of this week's weekly report based on the historical interaction information corresponding to the historical interaction events associated with writing the last weekly report that occurred in the document component with target object 150. In this way, embodiments of the present disclosure can further improve the content generation quality of digital assistants.

[0153] As another example, target object 150 may input the first message "Please write a weekly report for Project X" to digital assistant 102. Accordingly, digital assistant 102 may attach a summary of the associated meeting or a link to access the meeting minutes to the draft weekly report based on interaction pattern information determined in historical interaction information (e.g., reviewing meeting minutes before writing the weekly report). In this way, embodiments of the present disclosure can help improve the target object's information processing efficiency.

[0154] In some embodiments, the digital assistant 102 may also utilize the record entries maintained by the record module 210 to directly respond to the first information input by the target object 150, without relying on the target processing entity 140.

[0155] For example, target object 150 may input "Please help me find documents whose audience is Project Team X." Accordingly, digital assistant 102 can utilize the knowledge elements of the business objects maintained by record module 210 to respond to this input. Using Figure 3 as an example, knowledge element 355 of "Document A" may indicate "The audience is Project Team X." This allows digital assistant 102 to respond more accurately to target object 150's input.

[0156] It should be understood that the above document search is only an example scenario. By maintaining the knowledge elements of business objects, the embodiments of the present disclosure can greatly enrich the types of scenarios that the digital assistant can respond to.

[0157] As an example, by utilizing knowledge elements, digital assistants can more accurately respond to positioning search requests for target objects, such as "researched documents on XXX". As another example, by utilizing knowledge elements, digital assistants can also more accurately respond to discovery search requests for target objects, such as "what should I do if XX goes wrong". As another example, by utilizing knowledge elements, digital assistants can also more accurately respond to summaries of large amounts of data, such as "what work did project team A do in the first quarter". As another example, by utilizing knowledge elements, digital assistants can also provide personalized services for target objects. For example, digital assistants can provide target objects with inheritance based on creative style, for example, supporting the generation of new documents or emails based on the target object's existing creative style.

[0158] Example Process

[0159] FIG5 illustrates a flowchart of a process 500 for information processing according to some embodiments of the present disclosure. Process 400 may be implemented by an appropriate electronic device or combination of electronic devices (e.g., server 120, terminal device 110, or a combination of server 120 and terminal device 110 in FIG1 ). For ease of description, the following describes process 500 using server 120 as an example with reference to FIG1 .

[0160] As shown in the figure, in box 510, the server 120 generates historical interaction information for the interaction event based on the interaction event between the target object and at least one business component. The historical interaction information at least includes knowledge elements, which are used to describe the business object associated with the interaction event.

[0161] In box 520, the server 120 provides historical interaction information for the interaction between the target object and the digital assistant.

[0162] In some embodiments, the knowledge element indicates at least metadata of the business object.

[0163] In some embodiments, the business object includes a document type object, and the metadata includes at least one of the following: identification information of the document type object, user information of the document type object, the user information indicating at least one user associated with the document type object, time information of the document type object, the time information indicating the occurrence time of a historical event associated with the document type object, propagation information of the document type object, the propagation information indicating the degree of propagation of the document type object, permission information of the document type object, the permission information indicating the permission management policy of the document type object, and the business component to which the document type object belongs.

[0164] In some embodiments, the business object includes a session type object, and the metadata indicates a session type of the session type object, the session type including one or more of the following: topic session; internal session; external session; public session; single chat session; group chat session.

[0165] In some embodiments, a knowledge element describes at least the content of a business object.

[0166] In some embodiments, the business object includes a document type object, and the knowledge element indicates at least one of the following information about the content of the document type: completion status of the content, overview of the content, type of the content, keywords of the content, target users of the content, and style information of the content.

[0167] In some embodiments, the business object includes a document type object, the document type object includes a plurality of segments, and the knowledge element indicates a summary about each of the plurality of segments of the document type object.

[0168] In some embodiments, the multiple segments are split based on the structure of the document type object.

[0169] In some embodiments, the business object includes a session type object, and the knowledge element indicates at least one of the following: a functional description of the session type object, and an overview of message content in the session type object.

[0170] In some embodiments, the business object includes a session type object, a plurality of messages in the session type object are aggregated into a plurality of message sets, and the knowledge element indicates a summary about each of the plurality of message sets.

[0171] In some embodiments, the plurality of message sets are aggregated based on the time of the plurality of messages in the conversation type object; or the plurality of message sets are aggregated based on the topic to which the plurality of messages in the conversation belong.

[0172] In some embodiments, the knowledge element has a content structure corresponding to the type of the business object.

[0173] In some embodiments, the business object includes a document object, and the knowledge element is used to indicate a definition description of a group of non-common vocabulary included in the document object.

[0174] In some embodiments, the historical interaction information further includes an action element, where the action element is used to indicate the event type of the interaction event.

[0175] In some embodiments, the event type includes at least one of the following: a production event associated with a business object, a consumption event associated with a business object, a circulation event associated with a business object, a management event associated with a business object, and an interaction event associated with a business object.

[0176] In some embodiments, the historical interaction information further includes: a time element for indicating the time of occurrence of the interaction event; and / or a payload element for indexing a business object associated with the interaction event.

[0177] In some embodiments, process 500 also includes: obtaining first information input by the target object to the digital assistant; and generating second information based on at least the first information and historical interaction information as a response of the digital assistant to the first information.

[0178] In some embodiments, generating the second information based at least on the first information and the historical interaction information includes: processing the first information to generate third information based on the historical interaction information; providing the third information to the target processing entity; and generating the second information based on the processing result of the target processing entity on the third information.

[0179] In some embodiments, the third information includes guidance information, and the target processing entity includes a target model.

[0180] In some embodiments, the historical interaction information includes a set of record entries, and generating the second information based on at least the first information and the historical interaction information includes: determining at least one record entry associated with the first information from the set of record entries; and generating the second information based on the first information and the at least one record entry.

[0181] Example devices and equipment

[0182] FIG6 shows a schematic block diagram of an apparatus 600 for information processing according to certain embodiments of the present disclosure. Apparatus 600 may be implemented as or included in server 120, terminal device 110, or a combination of server 120 and terminal device 110 in FIG1 . Each module / component in apparatus 600 may be implemented by hardware, software, firmware, or any combination thereof.

[0183] As shown in the figure, the device 600 includes a generation module 610, which is configured to generate historical interaction information for the interaction event based on the interaction event between the target object and at least one business component, and the historical interaction information includes at least knowledge elements, which are used to describe the business object associated with the interaction event; and a providing module 620, which is configured to provide historical interaction information for the interaction between the target object and the digital assistant.

[0184] In some embodiments, the knowledge element indicates at least metadata of the business object.

[0185] In some embodiments, the business object includes a document type object, and the metadata includes at least one of the following: identification information of the document type object, user information of the document type object, the user information indicating at least one user associated with the document type object, time information of the document type object, the time information indicating the occurrence time of a historical event associated with the document type object, propagation information of the document type object, the propagation information indicating the degree of propagation of the document type object, permission information of the document type object, the permission information indicating the permission management policy of the document type object, and the business component to which the document type object belongs.

[0186] In some embodiments, the business object includes a session type object, and the metadata indicates a session type of the session type object, the session type including one or more of the following: topic session; internal session; external session; public session; single chat session; group chat session.

[0187] In some embodiments, a knowledge element describes at least the content of a business object.

[0188] In some embodiments, the business object includes a document type object, and the knowledge element indicates at least one of the following information about the content of the document type: completion status of the content, overview of the content, type of the content, keywords of the content, target users of the content, and style information of the content.

[0189] In some embodiments, the business object includes a document type object, the document type object includes a plurality of segments, and the knowledge element indicates a summary about each of the plurality of segments of the document type object.

[0190] In some embodiments, the multiple segments are split based on the structure of the document type object.

[0191] In some embodiments, the business object includes a session type object, and the knowledge element indicates at least one of the following: a functional description of the session type object, and an overview of message content in the session type object.

[0192] In some embodiments, the business object includes a session type object, a plurality of messages in the session type object are aggregated into a plurality of message sets, and the knowledge element indicates a summary about each of the plurality of message sets.

[0193] In some embodiments, the plurality of message sets are aggregated based on the time of the plurality of messages in the conversation type object; or the plurality of message sets are aggregated based on the topic to which the plurality of messages in the conversation belong.

[0194] In some embodiments, the knowledge element has a content structure corresponding to the type of the business object.

[0195] In some embodiments, the business object includes a document object, and the knowledge element is used to indicate a definition description of a group of non-common vocabulary included in the document object.

[0196] In some embodiments, the historical interaction information further includes an action element, where the action element is used to indicate the event type of the interaction event.

[0197] In some embodiments, the event type includes at least one of the following: a production event associated with a business object, a consumption event associated with a business object, a circulation event associated with a business object, a management event associated with a business object, and an interaction event associated with a business object.

[0198] In some embodiments, the historical interaction information further includes: a time element for indicating the time of occurrence of the interaction event; and / or a payload element for indexing a business object associated with the interaction event.

[0199] In some embodiments, the device 600 also includes an interaction module configured to: obtain first information input by the target object to the digital assistant; and generate second information based on at least the first information and historical interaction information as a response of the digital assistant to the first information.

[0200] In some embodiments, the interaction module is further configured to: process the first information to generate third information based on historical interaction information; provide the third information to the target processing entity; and generate second information based on the processing result of the target processing entity on the third information.

[0201] In some embodiments, the third information includes guidance information, and the target processing entity includes a target model.

[0202] In some embodiments, the historical interaction information includes a set of record entries, and the interaction module is further configured to: determine at least one record entry associated with the first information from the set of record entries; and generate the second information based on the first information and the at least one record entry.

[0203] FIG7 shows a block diagram of an electronic device 700 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 700 shown in FIG7 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 700 shown in FIG7 can be used to implement the server 70, the terminal device 110, or a combination of the server 70 and the terminal device 110 of FIG1 .

[0204] As shown in FIG7 , electronic device 700 is a general-purpose electronic device. Components of electronic device 700 may include, but are not limited to, one or more processors or processing units 710, memory 720, storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. Processing unit 710 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 720. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to enhance the parallel processing capabilities of electronic device 700.

[0205] The electronic device 700 typically includes a plurality of computer storage media. Such media can be any accessible media that can be obtained by the electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 720 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 730 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 700.

[0206] The electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 7 , a disk drive for reading from or writing to a removable, non-volatile disk (e.g., a “floppy disk”) and an optical drive for reading from or writing to a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 720 may include a computer program product 725 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0207] The communication unit 740 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 700 can be implemented as a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 700 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0208] Input device 750 may be one or more input devices, such as a mouse, keyboard, or trackball. Output device 760 may be one or more output devices, such as a display, a speaker, or a printer. Electronic device 700 may also communicate with one or more external devices (not shown) via communication unit 740 as needed, such as storage devices, display devices, or the like, with one or more devices that allow a user to interact with electronic device 700, or with any device that allows electronic device 700 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0209] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0210] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0211] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0212] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0213] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0214] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An information processing method, comprising: Based on an interaction event between a target object and at least one business component, generating historical interaction information for the interaction event, the historical interaction information at least including a knowledge element, the knowledge element being used to describe a business object associated with the interaction event; as well as The historical interaction information is provided for use in the interaction between the target object and the digital assistant. 2 . The method according to claim 1 , wherein the knowledge element comprises a first portion generated based on metadata of the business object.

3. The method according to claim 2, wherein the business object comprises a document type object, and the metadata comprises at least one of the following: identification information of the document type object, user information of the document type object, the user information indicating at least one user associated with the document type object, time information of the document type object, the time information indicating the occurrence time of a historical event associated with the document type object, Propagation information of the document type object, wherein the propagation information indicates the propagation degree of the document type object, The permission information of the document type object, wherein the permission information indicates a permission management policy of the document type object, The business component to which the document type object belongs.

4. The method of claim 2, wherein the business object comprises a session type object, and the metadata indicates a session type of the session type object, the session type comprising one or more of the following: Topic conversation; Internal Session; External Session; Public conversation; One-on-one chat session; Group chat session. The method of claim 1 , wherein the knowledge element comprises a second portion generated based on content of the business object.

6. The method of claim 5, wherein the business object comprises a document type object, and the second portion indicates at least one of the following: the completion status of the content, An overview of the content described, the type of content, Keywords of the content, The target audience of the content, Style information for the content. 7 . The method according to claim 5 , wherein the business object comprises a document type object, the document type object comprises a plurality of segments, and the knowledge element indicates a summary about each of the plurality of segments of the document type object. The method according to claim 7 , wherein the plurality of segments are split based on the structure of the document type object.

9. The method of claim 5, wherein the business object comprises a session type object, and the knowledge element indicates at least one of the following: Functional description of the session type object, An overview of the message content in the session type object.

10. The method according to claim 5, wherein the business object comprises a session type object, a plurality of messages in the session type object are aggregated into a plurality of message sets, and the knowledge element indicates an overview about each of the plurality of message sets.

11. The method according to claim 10, wherein: The plurality of message sets are aggregated based on the time of the plurality of messages in the conversation type object; or The plurality of message sets are aggregated based on topics to which the plurality of messages in the conversation belong.

12. The method according to claim 1, wherein the knowledge element has a content structure corresponding to the type of the business object.

13. The method according to claim 1, wherein the business object comprises a document object, and the knowledge element is used to indicate a definition description of a group of non-common vocabulary included in the document object.

14. The method according to claim 1, wherein the historical interaction information further includes an action element, and the action element is used to indicate the event type of the interaction event.

15. The method according to claim 14, wherein the event type comprises at least one of the following: production events associated with said business object, the consumption events associated with the business object, circulation events associated with the business object, management events associated with the business object, Interaction events associated with the business object.

16. The method according to claim 1, wherein the historical interaction information further comprises: A time element, used to indicate the time when the interaction event occurs; and / or The payload element is used to index the business object associated with the interaction event.

17. The method according to claim 1, further comprising: Acquire first information input by a target object to the digital assistant; as well as Based at least on the first information and the historical interaction information, second information is generated as a reply of the digital assistant to the first information.

18. The method according to claim 17, wherein generating second information based on at least the first information and the historical interaction information comprises: Based on the historical interaction information, processing the first information to generate third information; providing the third information to the target processing entity; as well as The second information is generated based on a processing result of the target processing entity on the third information. The method according to claim 18 , wherein the third information comprises guidance information, and the target processing entity comprises a target model.

20. The method according to claim 17, wherein the historical interaction information comprises a set of record entries, and generating the second information based at least on the first information and the historical interaction information comprises: determining at least one record entry associated with the first information from the set of record entries; as well as The second information is generated based on the first information and the at least one record entry.

21. An apparatus for information processing, comprising: A generating module, configured to generate historical interaction information for an interaction event between a target object and at least one business component based on the interaction event between the target object and the at least one business component, wherein the historical interaction information at least includes a knowledge element, and the knowledge element is used to describe a business object associated with the interaction event; as well as A providing module is configured to provide the historical interaction information for use in the interaction between the target object and the digital assistant.

22. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 20 when executed by the at least one processing unit.

23. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 20.

Images