Method, apparatus, device and storage medium for information processing

Abstract

According to embodiments of the present disclosure, methods, apparatuses, devices and storage media for information processing are provided. In one method, based on historical interaction information of a target object, aggregated information associated with the target object is generated, the historical interaction information is generated based on a set of interaction events between the target object and at least one business component; and the aggregated information is provided for interaction of the target object with a digital assistant. Thus, by generating a reply of the digital assistant based on the historical interaction information of the target object and the business component, embodiments of the present disclosure can improve the quality of the reply content generated by the digital assistant.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and more particularly to methods, apparatus, devices and computer-readable storage media for information processing. Background Technology

[0002] With the rapid development of internet technology, the internet has become an important platform for people to obtain and share content. Users can access the internet through terminal devices to enjoy various internet services.

[0003] Furthermore, internet platforms can provide users with capabilities related to the processing of various types of information. How to improve the accuracy of such information processing has become a focus of attention. Summary of the Invention

[0004] In a first aspect of this disclosure, an information processing method is provided. The method includes: generating aggregated information associated with a target object based on historical interaction information of that target object, the historical interaction information being generated based on a set of interaction events between the target object and at least one business component; and providing the aggregated information for use in interactions between the target object and a digital assistant.

[0005] In a second aspect of this disclosure, a method for information processing is provided. The method includes: determining time information of an interaction between a target object and a digital assistant; and providing at least one piece of content to the target object using the digital assistant, based at least on the time information, wherein the at least one piece of content is determined based on a match between the time information and aggregated information, the aggregated information being generated based on historical interaction information between the target object and at least one business component.

[0006] In a third aspect of this disclosure, a method for information processing is provided. The method includes: receiving first information input by a target object to a digital assistant, the first information indicating a content creation requirement; and using the digital assistant to provide the target object with created content, the created content being generated based on aggregated information associated with the target object, the aggregated information being generated based on historical interaction information between the target object and at least one business component.

[0007] In a fourth aspect of this disclosure, an apparatus for information processing is provided. The apparatus includes: a generation module configured to generate aggregated information associated with a target object based on historical interaction information of that target object, the historical interaction information being generated based on a set of interaction events between the target object and at least one business component; and a first providing module configured to provide the aggregated information for interaction between the target object and a digital assistant.

[0008] In a fifth aspect of this disclosure, an apparatus for information processing is provided. The apparatus includes: a determining module configured to determine a target time of interaction between a target object and a digital assistant; and a second providing module configured to provide at least one piece of content to the target object by the digital assistant, based at least on the target time, wherein the at least one piece of content is determined based on a match between the target time and aggregated information generated based on historical interaction information between the target object and at least one business component.

[0009] In a sixth aspect of this disclosure, an apparatus for information processing is provided. The apparatus includes: a receiving module configured to receive first information input by a target object to a digital assistant, the first information indicating a content creation requirement; and a third providing module configured to provide content to the target object by the digital assistant, the content being generated based on aggregated information associated with the target object, the aggregated information being generated based on historical interaction information between the target object and at least one business component.

[0010] In a seventh aspect of this 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 methods of the first, second, or third aspects.

[0011] In an eighth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program that can be executed by a processor to implement the methods of the first, second, or third aspects.

[0012] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0013] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0014] Figure 1 A schematic diagram of an example environment in which embodiments of the present disclosure can be implemented is shown;

[0015] Figure 2 A flowchart of a method for information processing according to some embodiments of the present disclosure is shown;

[0016] Figure 3An example system architecture according to some embodiments of this disclosure is shown;

[0017] Figure 4 A flowchart of a method for information processing according to some embodiments of the present disclosure is shown;

[0018] Figure 5 A flowchart of a method for information processing according to some embodiments of the present disclosure is shown;

[0019] Figure 6A , Figure 6B and Figure 6C A block diagram of an apparatus for information processing according to some embodiments of the present disclosure is shown; and

[0020] Figure 7 A block diagram of an apparatus capable of implementing several embodiments of the present disclosure is shown. Detailed Implementation

[0021] It is understood that before using the technical solutions disclosed in the embodiments of this disclosure, relevant users should be informed of the type, scope of use, and usage scenarios of the information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and their authorization should be obtained. The relevant users may include any type of rights holder, such as individuals, enterprises, or groups.

[0022] For example, upon receiving a user's active request, a prompt message is sent to the relevant user to explicitly inform them that the requested operation will require access to and use of their information. This allows the relevant user to autonomously choose, based on the prompt message, whether to provide information to the software or hardware such as the electronic device, application program, server, or storage medium performing the operations of this disclosed technical solution.

[0023] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, which can display the prompt message in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0024] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0025] It is understood 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) shall comply with the requirements of relevant laws, regulations and related provisions.

[0026] The term "in response to" as used herein refers to a state in which a corresponding event occurs or a condition is satisfied. It will be understood that the timing of subsequent actions performed in response to such event or condition is not necessarily strongly correlated with the time when the event occurs or the condition is met. For example, in some cases, subsequent actions may be performed immediately upon the occurrence of the event or the fulfillment of the condition; while in others, they may be performed some time after the occurrence of the event or the fulfillment of the condition.

[0027] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0028] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0029] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based 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 also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0030] As used herein, the term "model" refers to a system that learns the relationship between inputs and outputs from training data, enabling it to generate corresponding outputs for a given input after training. The generation and use of models 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 uses multiple layers of processing units to process inputs and provide corresponding outputs. In this document, "model" may also be referred to as a "machine learning model," a "machine learning network," or simply a "network," and these terms are used interchangeably. A model can also include different types of processing units or networks.

[0031] As briefly mentioned earlier, people can already utilize 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).

[0032] However, such information processing is usually a generalized capability, which limits the types of tasks that digital assistants can handle.

[0033] Embodiments of this disclosure provide a scheme for information processing. Specifically, aggregated information associated with a target object (e.g., a user or termination) is generated based on historical interaction information of the target object, wherein the historical interaction information is generated based on a set of interaction events between the target object and at least one business component. Further, the aggregated information can be provided for interaction between the target object and a digital assistant.

[0034] Therefore, the embodiments of this disclosure can obtain aggregated information by extracting historical interaction information between the target object and business components, which can then be used for the interaction of the digital assistant, thereby supporting the digital assistant to provide richer interactive capabilities.

[0035] Example embodiments of this disclosure are described below with reference to the accompanying drawings.

[0036] Example Environment

[0037] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. For example... Figure 1 As shown, in environment 100, terminal device 110 can be used to provide digital assistant 102 to target object 150. Such target object may include users or organizations, where the organization may be a company, group, department, etc.

[0038] For example, such a digital assistant 102 could also be called a digital assistant or a digital robot. It should be understood that, although in Figure 1 The digital assistant 102 is shown to be included in the terminal device 110, but some 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.

[0039] In some examples, digital assistant 102 may be, for example, a digital assistant that assists target object 150 in its work, or any other suitable entity. Digital assistant 102 may also operate independently or be integrated into a specific application.

[0040] In some embodiments, the digital assistant 102 can be activated by an appropriate means (e.g., a shortcut key, a button, or voice), such as being invoked or woken up. 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 a conversational user interface (also referred to as a conversational interface or conversational window) or any other suitable interface form. As will be described in detail below, such an interface 104 may also include interface elements for information interaction, such as message input boxes, message lists, message bubbles, etc. Through the interface 104, the digital assistant 102 can obtain information input by the target object 150 (also referred to as first information).

[0041] Such input information can include any appropriate type of message, such as text messages, image messages, voice messages, form messages, link messages, and other appropriate types of messages.

[0042] Furthermore, server 120 may allow target object 150 to interact with digital assistant 102 to obtain information generated by digital assistant 102. Alternatively, as will be detailed below, with authorization from target object 150, the information generated by digital assistant 102 may also be based on historical interactions between target object 150 and at least one business component 115. For example, digital assistant 102 may use historical interaction information 130 generated based on historical interaction events between target object 150 and at least one business component 115 to process the first information.

[0043] Such a business component 115 may include components capable of providing appropriate types of business services to the target object 150, examples of which may include, but are not limited to, office-related components, tool-related components, etc. In some embodiments, such a business component may be installed on the same terminal device 110. Alternatively or additionally, such a business component may also be installed on other terminal devices or provided as a cloud service.

[0044] In some embodiments, such a business component 115 may include multiple office components within an office suite. An office suite can 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 charting, and so on.

[0045] In some embodiments, the multiple office components include a number of the following: chat components, document components, audio and video conferencing components, email components, calendar components, schedule components, task components, Objectives and Key Results (OKR) components, and / or appropriate office components that are currently available or may be developed in the future.

[0046] In some embodiments, digital assistant 102 may be a separate application from business component 115. Alternatively, digital assistant 102 may also be a function or component appropriately integrated into business component 115.

[0047] In some embodiments, historical interaction information 130 may be maintained as needed on appropriate electronic devices, such as terminal device 110, server 120, and / or other appropriate electronic devices. Historical interaction information 130 may include, for example, interaction information stored on terminal device 110 or interaction information uploaded to server 120.

[0048] In some embodiments, aggregated information 135 can also be generated based on the extraction of historical interaction information 130. Furthermore, the digital assistant 102 can also use the aggregated information 135 to interact with the target object 150.

[0049] As will be detailed below, historical interaction information 130 and / or aggregated information 135 can be provided for interaction between digital assistant 102 and target object 150. As an example, digital assistant 102 can obtain input information from target object 150, and digital assistant 102 or server 120 can generate corresponding information (also referred to as third information) based on the input information and historical interaction information 130 and / or aggregated information 135.

[0050] Furthermore, the server 120 or digital assistant 102 can send the generated third information to the target processing entity 140. Furthermore, the server 120 or digital assistant 102 can 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 can, for example, be presented to the target object 150 via an interface 104 corresponding to the digital assistant 102.

[0051] The target processing entity 140 can be a processing entity based on appropriate information processing technology, and can perform one or more functions such as text generation, image generation, summarization, encoding, translation, and chatbot. The target processing entity 140 can also be any other appropriate entity form.

[0052] In some embodiments, terminal device 110 communicates with server 120 to provide services to digital assistant 102. Terminal device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, terminal device 110 can also support any type of interface for target object 150 (such as "wearable" circuitry). Server 120 can be various types of computing systems / servers capable of providing computing power, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, etc.

[0053] Despite Figure 1 Only one server 120 is shown, but environment 100 may include multiple servers 120. For example, historical interaction information 130 may be stored locally, or on a second server 120, as needed and with relevant user authorization, and the target processing entity 140 may 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 this disclosure.

[0054] It should be understood that the structure and function of environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0055] Example process

[0056] Figure 2 A flowchart of a process 200 for information processing according to some embodiments of the present disclosure is shown. Process 200 may be implemented by suitable electronic devices or a combination of electronic devices (e.g., Figure 1 (This refers to server 120, terminal device 110, or a combination of server 120 and terminal device 110). For ease of description, server 120 is used as an example below, and references are also provided. Figure 1 To describe process 200.

[0057] In box 210, server 120 generates aggregate information 135 associated with target object 150 based on historical interaction information 130 of target object 150, wherein historical interaction information 130 is generated based on a set of interaction events between target object 150 and at least one business component 115.

[0058] The following will be referenced Figure 3 This describes the generation and management process of historical interaction information 130 and aggregated information 135. Figure 3 An example system architecture 200 according to an embodiment of the present disclosure is shown.

[0059] like Figure 3 As shown, when the target object 150 interacts with the business component 115, the business component 115 can generate log records and send the log records to the recording module 310.

[0060] Furthermore, the recording module 310 can generate corresponding record entries based on the received log records and construct a record library as historical interaction information. In some embodiments, such record entries may include knowledge elements to describe the business objects corresponding to the historical interaction events. In some embodiments, the record library may be maintained and processed by appropriate electronic devices, such as being stored at the terminal device 110 or at the server 120.

[0061] In some embodiments, such business objects may include business objects generated by the target object 150 during its interaction with the business component 115, edited business objects, referenced business objects, shared business objects, etc. Taking the business component 115 as a document component as an example, historical interaction events may include creation events of a specific document in the document component by the target object 150. Accordingly, the business object corresponding to the document creation event is that specific document.

[0062] In some embodiments, the knowledge element may be a natural language description of the business object, designed to abstract and / or compress the content of the business object. For example, using a document object as an example of a business object, the knowledge element may be used to describe the document object's topic, completion status, audience, language, and style of expression, etc.

[0063] It should be understood that different dimensions of information can be selected to generate knowledge elements that describe the business object, depending on the type of the business object. For example, taking a session as an example of a business object, knowledge elements could be used to describe the type of session (e.g., whether it is a one-on-one chat), an overview of the session, etc.

[0064] Therefore, by maintaining knowledge elements in the record entries, embodiments of this disclosure can describe or characterize the business objects involved in the corresponding historical interaction events with a limited content length.

[0065] In some embodiments, record entries may also include a time element indicating when a historical interaction event occurred. For example, continuing with the example of document creation as a historical interaction event, such a time element could indicate the document's creation time.

[0066] In some other embodiments, the record entry may also include an action element that indicates the type of the historical interaction event. Continuing with the example of creating a document as a historical interaction event, such an action element could, for example, indicate that the type of the historical interaction event is "create".

[0067] In some embodiments, a record entry may further include a payload element for indexing a business object corresponding to a relevant 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.

[0068] Therefore, in some scenarios, after the target object 150 interacts with the business component 115, the recording module 310 can generate corresponding record entries. Such record entries can be represented as {time element, action element, knowledge element, payload element} to describe the historical interaction event from multiple preset dimensions.

[0069] In this way, the recording module 310 can support the interaction between the target object 150 and the digital assistant 102 by maintaining a set of record entries in the record library. Such a record library can also be similar to the digital assistant's "memory information," thereby helping the digital assistant improve the quality of the generated response content.

[0070] In some embodiments, considering that as the target object 150 interacts more and more with the business component 115, the size of its corresponding record library will also increase. In order to manage historical interaction information more effectively, the record module 310 can also perform compression processing on the record entries.

[0071] For example, the recording module 310 may periodically compress record entries in the record library to compress multiple record entries into a single compressed record entry. For instance, the recording module 310 may perform record entry compression based on the occurrence time of historical interaction events.

[0072] In some embodiments, if multiple historical interaction events have occurred for more than a threshold duration (e.g., one month), the recording module 310 can remove the record entries for the multiple historical interaction events from the record library and generate corresponding compressed record entries.

[0073] For example, the recording module 310 can identify a set of record entries to be compressed from the record library. Such a set of record entries to be compressed may correspond to associated interaction events whose occurrence date has exceeded a threshold duration (e.g., associated with the same business object).

[0074] For example, target object 150 may have created, edited, and shared document A within a week a month ago. Accordingly, the record library could previously maintain three record entries corresponding to these three historical interaction events. Furthermore, the record module 310, upon determining that all three historical interaction events occurred a month ago, can compress the three record entries into a single compressed record entry.

[0075] In the process of compressing multiple record entries into a single compressed record entry, the record module 310 may, for example, retain only the important information from the multiple record entries, thereby reducing the storage and management overhead of the record entries.

[0076] In some embodiments, the method of compressing record entries may also include retaining a portion of the record entries to be compressed. Continuing with the examples of creating document A, editing document A, and sharing document A, the recording module 310 may, for example, retain only the record entry corresponding to "editing document A," which may also be referred to as the record compression entry.

[0077] This recording method is similar to how human memory is managed. That is, for historical events from earlier times, the recording module can maintain relatively vague information, while for historical events from more recent times, the recording module can maintain more accurate information.

[0078] In some embodiments, the recording module 310 may utilize a compression model to compress the record entries. Specifically, the recording module 310 may provide multiple record entries to be compressed to the recording model to obtain record compression entries corresponding to the multiple record entries to be compressed. Such a compression model may be implemented using an appropriate machine learning model.

[0079] In some examples, the compression model can be a reference. Figure 1 The target processing entity 140 under discussion. That is, the recording module 310 can obtain the compressed record entry by providing the target processing entity 140 with a guide word to instruct the target processing entity 140 to perform compression and multiple record entries to be compressed. For example, such a guide word could 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".

[0080] In this way, the recording module 310 can, for example, periodically compress recording entries to reduce the management and maintenance costs of recording entries.

[0081] In some embodiments, if the target object 150 is aware of and authorizes the recording module 310, the recording module 310 may also reflect the recording entries to generate aggregated information 135 associated with the target object 150.

[0082] In some embodiments, the recording module 310 may determine the correlation between at least two elements among multiple elements in the historical interaction information 130 and may generate aggregate information 135 to indicate the correlation.

[0083] For example, such aggregated information 135 can indicate the correlation between time elements and action elements. For instance, the recording module 310 can analyze multiple record entries in the historical interaction information 130 to determine the correlation between time elements and action elements, such as "write a weekly report every Monday afternoon".

[0084] As another example, such aggregated information 135 can also indicate the correlation between action elements and knowledge elements. For example, the recording module 310 can analyze multiple record entries in the historical interaction information 130 to determine the correlation between action elements and knowledge elements, such as "Document A was updated with the following content in the last month: XXX".

[0085] In this way, embodiments of the present disclosure can generate aggregated information 135 by extracting the correlation between different elements.

[0086] In some embodiments, the aggregation information 135 may be used to describe the characteristics of the target object 150 and / or the characteristics of the associated entities of the target object 150.

[0087] Specifically, the recording module 310 can extract aggregated information at different levels. For example, the recording module 310 can extract the working characteristics of the target object 150, such as "the target object writes a weekly report every Monday afternoon".

[0088] As another example, the recording module 310 can also extract the characteristics of the associated entities of the target object. Such associated entities may include groups associated with the target object, organizations associated with the target object, or projects associated with the target object.

[0089] For example, the recording module 310 can extract the characteristics of the projects in which the target object 150 participates. For example, the aggregated information 135 can indicate an overview of the project, such as the project's progress, next steps, and responsible personnel.

[0090] As another example, the recording module 310 can extract characteristics of the organization (e.g., department) to which the target object 150 belongs. For example, aggregated information 135 can indicate the main tasks completed by the department in the most recent month.

[0091] In this way, the recording module 310 can extract information such as knowledge elements and action elements from different levels, thereby obtaining aggregated information corresponding to different levels.

[0092] In some embodiments, the recording module 310 may utilize an aggregation model to generate aggregation information 135. Specifically, the recording module 310 may generate information to be provided to the aggregation model based on historical interaction information 130. For example, multiple record entries to be refined may be provided to the aggregation model to obtain one or more descriptive entries corresponding to the multiple record entries to be refined. Such an aggregation model may be implemented using an appropriate machine learning model.

[0093] In some examples, the aggregation model can be a reference. Figure 1 The target processing entity 140 under discussion. That is, the recording module 310 can obtain refined aggregated information by providing the target processing entity 140 with guide words to guide the target processing entity 140 in performing feature extraction and multiple record entries to be extracted.

[0094] Based on the above methods, the recording module 310 may maintain one or more of the following: record entries corresponding to historical interaction events, record compression entries obtained by compressing record entries, and / or aggregated information obtained by refining record entries, for use in the generation of second information.

[0095] Continue to refer to Figure 2 In box 220, server 120 provides aggregated information for the interaction between the target object and the digital assistant.

[0096] In some embodiments, as referenced Figure 1 As discussed, server 120 can use target processing entity 140 to generate second information.

[0097] Specifically, server 120 can process the first information based on record entries, record compression entries, and / or aggregated information 135 maintained by record module 310 to generate third information. Further, server 120 can provide the third information to target processing entity 140, wherein target processing entity 140 is different from digital assistant 102. Additionally, server 120 can generate second information based on the processing result of the third information by target processing entity 140.

[0098] In some embodiments, the target processing entity 140 may include a target model, such as a target language model. Accordingly, third information may include, for example, input information to the target model. In some scenarios, such third information may also be referred to as a prompt, guide word, or alert 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 other suitable models.

[0099] In some embodiments, 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 310.

[0100] It should be understood that any suitable technique can be used to determine at least one record entry associated with the first information. For example, server 120 can determine at least one record entry semantically associated with the first information from the set of record entries based on semantic analysis of the first information. Alternatively, server 120 can also determine at least one record entry semantically associated with the first information from a record database, for example, based on keyword search or matching.

[0101] As an example, server 120 may determine at least one associated record entry based on the 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 the record database and a target description vector corresponding to the received first information. Further, 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.

[0102] As an example, server 120 may determine from the set of record entries that the angle between the corresponding description vector and the target description vector is less than a threshold, as at least one record entry associated with the first information.

[0103] Accordingly, server 120 can also generate third information to be provided to target processing entity 140 based on the first information and at least one associated record entry. For example, server 120 can generate third information by adding additional information corresponding to at least one associated record entry while retaining the first information. Exemplarily, such additional information can be generated based on at least one associated record entry.

[0104] For example, server 120 may provide all or part of the knowledge elements of "Document A" as third information to target processing entity 140. For instance, server 120 may provide the portion of knowledge element 355 that represents the style information of "Document A" as "the language expression of the document is formal" to target processing entity 140, so that target processing entity 140 can respond to the first information based on the style information.

[0105] As another example, server 120 may also rewrite the first information based on at least one associated record entry, for example, by expanding the first information so that the first information can more accurately reflect the needs of target object 150.

[0106] In some embodiments, server 120 may also process the first information based on a set of compressed record entries included in historical interaction information 130 to generate the second information. Exemplarily, similar to the process of determining associated compressed record entries, server 120 may determine at least one compressed record entry associated with the first information from the set of compressed record entries maintained by recording module 310.

[0107] Furthermore, server 120 can use the determined at least one record compression entry and the first information to generate third information to be provided to target processing entity 140. For example, server 120 can add additional information corresponding to the associated at least one record compression entry while retaining the first information to generate the third information. Exemplarily, such additional information can be generated based on the associated at least one record compression entry.

[0108] As another example, server 120 may also rewrite the first information based on at least one associated record compression entry, for example, by expanding the first information so that the first information can more accurately reflect the needs of target object 150.

[0109] In some embodiments, server 120 may also process the first information based on aggregated information 135 to generate second information. Such aggregated information 135 may, for example, include a set of descriptive entries used to describe different aspects. Exemplarily, server 120 may determine, for example, at least one descriptive entry associated with the first information from this set of descriptive entries.

[0110] Furthermore, server 120 can use the determined at least one description entry and the first information to generate third information to be provided to target processing entity 140. For example, server 120 can add additional information corresponding to the associated at least one description entry while retaining the first information to generate the third information. Exemplarily, such additional information can be generated based on the associated at least one description entry.

[0111] As another example, server 120 may also rewrite the first information based on at least one associated description entry, for example, by expanding the first information so that the first information can more accurately reflect the needs of target object 150.

[0112] Based on this approach, embodiments of this disclosure can generate third information that better meets the interaction needs of the target object 150 based on aggregated information 135, thereby improving the accuracy of information processing while the target object maintains its personal interaction habits.

[0113] Furthermore, the terminal device 110 may also acquire 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.

[0114] The above discussion illustrates an example process by which the digital assistant 102 generates second information based on the first information input by the target object 150. Based on the above approach, the embodiments of this disclosure can improve the accuracy of information processing, making the generated second information more in line with the interaction habits of the target object 150 and its needs for interaction results.

[0115] In some embodiments, server 120 may also determine at least one description entry associated with the first information from aggregated information 135 and directly use the description entry to generate a response without using target processing entity 140.

[0116] The process of determining relevant descriptive entries will be described below in conjunction with the first information for different types of needs. In some embodiments, the first information received by the digital assistant 102 may indicate a location-based search need for specific content. For example, the first information may be "Please help me list my project weekly report".

[0117] Furthermore, server 120 can determine a matching first description entry from aggregated information 135 based on the first information and / or the target attribute of the first information (e.g., the event in which the first information was received is Monday). For example, the first description entry may indicate historical interaction attribute information of the target object, such as "the target object attends the weekly meeting of Project A every Monday afternoon".

[0118] Accordingly, when providing weekly reports, server 120 can prioritize providing project weekly reports on "Project A" as the corresponding recommended content. Thus, the recommended content provided by server 120 can better match the needs of the target object. In some embodiments, server 120 can directly utilize aggregated information 135 to provide project weekly reports on "Project A"; alternatively, server 120 can also utilize the determined first description entry to process the first information, thereby utilizing target processing entity 140 to provide project weekly reports on "Project A".

[0119] Therefore, by utilizing aggregated information, embodiments of this disclosure can more accurately respond to location-based search needs for target objects.

[0120] In some embodiments, the first information received by the digital assistant 102 may indicate a content creation requirement for a specific topic. For example, the target object 150 may input the following first information: "Please help draft the weekly report for Project A".

[0121] Furthermore, server 120 can determine a second description entry that matches the first information from aggregated information 135, such a second description entry can indicate the creative attribute information of target object 150.

[0122] For example, the aggregated information 135 may include a second descriptive entry, which may be generated based on the extraction of creative style information from weekly reports created by the target object 150 within a predetermined period of time. Furthermore, the server 120 may, for example, directly generate corresponding creative content based on the second descriptive entry as the second information.

[0123] Alternatively, server 120 may also use the determined second description entry to process the first information, so as to use target processing entity 140 to create a corresponding weekly report draft as the second information. For example, server 120 may provide the second description entry together with the first information to target processing entity 140, so that target processing entity 140 can generate corresponding creative content according to the creative attribute information indicated by the second description entry.

[0124] In this way, the embodiments of this disclosure can better match the creative attribute information of the target object, thereby making the generated content more in line with the expectations of the target object.

[0125] In some embodiments, the interaction between the digital assistant 102 and the target object 150 may include not only the conversational interaction discussed above, but also the provision of corresponding recommended content by the digital assistant 102 to the target object 150.

[0126] For example, server 120 may generate recommended content for target object 150 based on the aggregated information determined above, and digital assistant 102 may provide the recommended content to target object 150.

[0127] As an example, such recommended content may include at least one item for input into an appropriate input control associated with digital assistant 102. For instance, for a search input control in a document component, digital assistant 102 may provide documents associated with "Project A" as recommended content based on the description entry "The target object attends Project A's weekly meeting every Monday afternoon" included in aggregate information 135, based on the target object 150 opening the document component "Monday morning". For example, such recommended content may include "Want to search for Project A's weekly report?" etc. It should be understood that the search control is only one example of an input control, and any other appropriate input control may be included.

[0128] As another example, such recommendations may also include at least one piece of recommended content for input into the digital assistant 102, such as recommended prompts. For example, the digital assistant 102 may provide candidate prompts to the target user at the time "Monday afternoon" based on the description entry "The target user writes a weekly report every Monday afternoon" included in the aggregated information 135, such as "Please draft the weekly report".

[0129] In this way, embodiments of the present disclosure can utilize aggregated information to improve the efficiency of interaction between the target object and the digital assistant.

[0130] Figure 4 A flowchart of a method 400 for information processing according to some embodiments of the present disclosure is shown. Method 400 may be implemented by suitable electronic devices or a combination of electronic devices (e.g., Figure 1 (The server 120, terminal device 110, or a combination of server 120 and terminal device 110).

[0131] like Figure 4 As shown, in box 410, an electronic device (e.g., server 120) determines the timing information of the target object's interaction with the digital assistant.

[0132] For example, when the target object 150 interacts with the digital assistant 102, the time information corresponding to the interaction can be determined. Such time information can have appropriate precision, such as a specific moment, a particular day, or a particular month.

[0133] In box 520, based at least on time information, an electronic device (e.g., server 120) uses a digital assistant to provide at least one piece of content to a target object, wherein the at least one piece of content is determined based on a match between time information and aggregated information, which is generated based on historical interaction information between the target object and at least one business component.

[0134] The specific process for generating historical interaction information can be found in the description above, and will not be repeated here. Furthermore, such aggregated information can be derived from aggregated information. For example, such aggregated information can indicate the correlation between the occurrence time and event type of a set of interaction events.

[0135] For example, aggregated information can indicate that "the target audience attends the A project meeting every Wednesday afternoon." Based on this aggregated information and the corresponding time information of the interaction (e.g., Wednesday), the digital assistant 102 can proactively provide search guidance or content entry points related to "A project."

[0136] Alternatively, for the first piece of information input by the target 150, the digital assistant 102 can also process it accordingly based on matching time information with aggregated information. For example, if the information input by the target 150 is "Looking for weekly reports", in the case of matching time information (e.g., Wednesday) with aggregated information, the digital assistant 102 can, for example, prioritize providing weekly reports related to "Project A" as a response to the first piece of information.

[0137] In this way, embodiments of the present disclosure can improve the efficiency of digital assistant information processing and enable the provided content to better meet the needs of the target audience.

[0138] Figure 5 A flowchart of a method 400 for information processing according to some embodiments of the present disclosure is shown. Method 400 may be implemented by suitable electronic devices or a combination of electronic devices (e.g., Figure 1 (The server 120, terminal device 110, or a combination of server 120 and terminal device 110).

[0139] like Figure 5 As shown, in box 510, an electronic device (e.g., terminal device 110) receives first information input by the target object to the digital assistant, the first information indicating content creation needs.

[0140] As discussed above, the target object 150 may input first information into the digital assistant 102, such as, "Please help draft the weekly report for project A".

[0141] In box 520, a digital assistant is used to provide creative content to the target object. The creative content is generated based on aggregated information associated with the target object, which is generated based on the historical interaction information between the target object and at least one business component.

[0142] Furthermore, server 120 can determine a description entry matching the first information from aggregated information 135. Such a description entry can indicate the creative attribute information of target object 150. For example, aggregated information 135 may include a description entry that can be generated based on the extraction of creative style information of weekly reports created by target object 150 within a predetermined period of time. Furthermore, server 120 can, for example, directly generate corresponding creative content based on the description entry as the second information.

[0143] Alternatively, server 120 may also use the determined description entries to process the first information, so as to use target processing entity 140 to create a corresponding weekly report draft as the second information. For example, server 120 may provide the second description entries together with the first information to target processing entity 140, so that target processing entity 140 can generate corresponding creative content according to the creative attribute information indicated by the second description entries.

[0144] Based on this approach, embodiments of this disclosure can enable digital assistants to generate corresponding creative content based on the creative attribute information of the target object, making its style more compatible with the target object.

[0145] Example devices and equipment

[0146] Figure 6A A schematic structural block diagram of an apparatus 400 for information processing according to certain embodiments of the present disclosure is shown. The apparatus 600A may be implemented as or included in... Figure 1 The device 600A comprises server 120, terminal device 110, or a combination of server 120 and terminal device 110. Each module / component in the device 600A can be implemented by hardware, software, firmware, or any combination thereof.

[0147] As shown in the figure, the device 600A includes a generation module 610 configured to generate aggregated information associated with the target object based on the target object's historical interaction information, wherein the historical interaction information is generated based on a set of interaction events between the target object and at least one business component; and a first providing module 620 configured to provide aggregated information for the interaction between the target object and the digital assistant.

[0148] In some embodiments, historical interaction information includes at least one of the following: a knowledge element, which describes the business object corresponding to the corresponding interaction event; an action element, which indicates the event type of the corresponding interaction event; and a time element, which indicates the time when the corresponding interaction event occurred.

[0149] In some embodiments, historical interaction information includes multiple elements corresponding to different types, and generating aggregate information associated with a target object includes: determining the correlation between at least two elements among the multiple elements of the historical interaction information; and generating aggregate information to indicate the correlation.

[0150] In some embodiments, the aggregated information is used to describe the characteristics of the target object and / or its associated entities.

[0151] In some embodiments, the associated entities of the target object include: a group associated with the target object; an organization associated with the target object; and a project associated with the target object.

[0152] In some embodiments, the generation module 610 is further configured to: generate fourth information based on historical interaction information; and provide the fourth information to the aggregation model to generate aggregation information.

[0153] In some embodiments, the device 600A further includes an interaction module configured to acquire first information input by a target object to a digital assistant; and to generate second information based at least on the first information and aggregated information as a response from the digital assistant to the first information.

[0154] In some embodiments, the interaction module is further configured to: process first information based on aggregated information to generate third information; provide the third information to a target processing entity; and generate second information based on the processing result of the target processing entity on the third information.

[0155] In some embodiments, the third information includes guidance information, and the target processing entity includes the target model.

[0156] In some embodiments, the aggregated information includes a set of descriptive entries, and the interaction module is further configured to: determine at least one descriptive entry associated with the first information from the set of descriptive entries; and generate second information based on the first information and the at least one descriptive entry.

[0157] In some embodiments, the first information indicates a location-based search request for specific content, and the interaction module is further configured to: determine a matching first description entry from a set of description entries based on the first information and / or the target attributes of the first information, wherein the first description entry indicates historical interaction attribute information of the target object, and wherein the generated second information indicates recommended content generated based on the first description entry.

[0158] In some embodiments, the first information indicates content creation requirements, and the interaction module is further configured to: determine a matching second description entry from a set of description entries, wherein the second description entry indicates creation attribute information of the target object, and wherein the generated second information indicates creation content generated based on the second description entry.

[0159] In some embodiments, the first information also indicates historical content for reference, and the matching second description entry is generated based on historical interaction events associated with the historical content.

[0160] In some embodiments, the device 600A further includes a recommendation module configured to generate recommended content for a target object based on aggregated information, so that the digital assistant can provide the recommended content.

[0161] In some embodiments, the recommended content includes: at least one recommended content for input into a target input control; and / or at least one recommended content for input into a digital assistant.

[0162] Figure 6B A schematic structural block diagram of an apparatus 400 for information processing according to certain embodiments of the present disclosure is shown. Apparatus 600B may be implemented as or included in... Figure 1 The various modules / components in the device 600B can be implemented by hardware, software, firmware, or any combination thereof. (The text also mentions server 120, terminal device 110, or a combination of both.)

[0163] As shown in the figure, the device 600B includes a generation module 610 configured to generate aggregated information associated with the target object based on the target object's historical interaction information, wherein the historical interaction information is generated based on a set of interaction events between the target object and at least one business component; and a first providing module 630 configured to provide aggregated information for the interaction between the target object and the digital assistant.

[0164] In some embodiments, historical interaction information is generated based on a set of interaction events between a target object and at least one business component, and the aggregated information at least indicates the correlation between the occurrence time and event type of a set of interaction events.

[0165] Figure 6C A schematic structural block diagram of an apparatus 400 for information processing according to certain embodiments of the present disclosure is shown. The apparatus 600C may be implemented as or included in... Figure 1 The various modules / components in the device 600C can be implemented by hardware, software, firmware, or any combination thereof.

[0166] As shown in the figure, the device 600C includes a receiving module 650 configured to receive first information input by a target object to a digital assistant, the first information indicating content creation requirements; and a third providing module 660 configured to provide creative content to the target object by the digital assistant, the creative content being generated based on aggregated information associated with the target object, the aggregated information being generated based on historical interaction information between the target object and at least one business component.

[0167] In some embodiments, historical interaction information is generated based on a set of interaction events between the target object and at least one business component, and the aggregated information at least indicates the creation attribute information of the target object, which is determined based on the creation attributes of at least one business object corresponding to the set of interaction events.

[0168] Figure 7 A block diagram is shown illustrating an electronic device 700 in which one or more embodiments of the present disclosure may be implemented. It should be understood that... Figure 7 The electronic device 700 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 7 The electronic device 700 shown can be used to achieve Figure 1 The server 120, the terminal device 110, or a combination of the server 120 and the terminal device 110.

[0169] like Figure 7 As shown, electronic device 700 is in the form of 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 physical or virtual processor and is capable of performing various processes according to programs stored in memory 720. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 700.

[0170] Electronic device 700 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 720 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 730 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 700.

[0171] Electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 7 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 720 may include computer program product 725 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0172] The communication unit 740 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 700 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 700 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0173] Input device 750 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 760 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 700 can also communicate with one or more external devices (not shown) via communication unit 740 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 700, or with any device that enables electronic device 700 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0174] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0175] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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: Based on the historical interaction information of the target object, aggregated information associated with the target object is generated; wherein, the historical interaction information is generated based on a set of interaction events between the target object and at least one business component, the set of interaction events being interaction events between the target object and business objects within the business component, the historical interaction information includes a set of record entries generated based on the set of interaction events, each record entry describing a corresponding interaction event, the record entry including at least one of the following: a knowledge element describing the business object corresponding to the corresponding interaction event; an action element indicating the event type of the corresponding interaction event; a time element indicating the occurrence time of the corresponding interaction event, the aggregated information indicating the correlation between at least two elements in the historical interaction information, the correlation being determined by analyzing multiple record entries corresponding to multiple interaction events; and The aggregated information is provided for the interaction between the target object and the digital assistant.

2. The method according to claim 1, wherein the aggregation information is further used to describe the characteristics of the target object and / or the characteristics of the associated entities of the target object.

3. The method according to claim 2, wherein the associated entity of the target object comprises: The group associated with the target object; The organization associated with the target object; The project associated with the target object.

4. The method of claim 1, wherein generating aggregate information associated with the target object comprises: A fourth piece of information is generated based on the historical interaction information; The fourth information is provided to the aggregation model to generate the aggregation information.

5. The method according to claim 1, further comprising: Obtain the first information input by the target object to the digital assistant; as well as Based at least on the first information and the aggregated information, second information is generated as the digital assistant's response to the first information.

6. The method of claim 5, wherein generating the second information based at least on the first information and the aggregated information comprises: Based on the aggregated information, the first information is processed to generate the third information; Provide the third information to the target processing entity; as well as The second information is generated based on the processing result of the target processing entity on the third information.

7. The method according to claim 6, wherein the third information includes guidance information, and the target processing entity includes a target model.

8. The method of claim 5, wherein the aggregated information comprises a set of descriptive entries, and generating second information based at least on the first information and the aggregated information comprises: Determine at least one description entry from the set of description entries that is associated with the first information; as well as The second information is generated based on the first information and the at least one description entry.

9. The method of claim 8, wherein the first information indicates a search need for specific content. Determining at least one description entry associated with the first information from the set of description entries includes: Based on the first information and / or the target attributes of the first information, a matching first description entry is determined from the set of description entries, wherein the first description entry indicates the historical interaction attribute information of the target object. The generated second information indicates recommended content generated based on the first description entry.

10. The method according to claim 8, wherein the first information indicates content creation requirements. Determining at least one description entry associated with the first information from the set of description entries includes: A matching second description entry is determined from the set of description entries, wherein the second description entry indicates the creative attribute information of the target object. The generated second information indicates the creative content generated based on the second description entry.

11. The method of claim 10, wherein the first information further indicates historical content for reference, and the matched second description entry is generated based on historical interaction events associated with the historical content.

12. The method according to claim 1, further comprising: Based on the aggregated information, recommended content is generated for the target object, so that the digital assistant can provide the recommended content.

13. The method of claim 12, wherein the recommended content includes: At least one recommended item is used to input into the target input control; and / or At least one recommended content is used to input into the digital assistant.

14. The method of claim 12, wherein the recommended content includes content related to at least one planned event of the target object, wherein the at least one planned event is determined based on the aggregated information.

15. The method of claim 14, wherein the at least one planned event is determined based on the periodic characteristics indicated by the aggregated information, to indicate that the target object is expected to participate in the planned event according to a specific time period.

16. An information processing method, comprising: Determine the timing information of the interaction between the target object and the digital assistant; as well as Based at least on the time information, the digital assistant provides at least one piece of content to the target object. This at least one piece of content is determined based on a match between the time information and aggregated information. The aggregated information is generated based on historical interaction information between the target object and at least one business component. The historical interaction information is generated based on a set of interaction events between the target object and a business object within the business component, and includes a set of record entries generated based on the set of interaction events. Each record entry describes a corresponding interaction event and includes at least one of the following: a knowledge element describing the business object corresponding to the corresponding interaction event; an action element indicating the event type of the corresponding interaction event; and a time element indicating the time of occurrence of the corresponding interaction event. The aggregated information indicates the correlation between at least two elements in the historical interaction information, and this correlation is determined by analyzing multiple record entries corresponding to multiple interaction events.

17. The method of claim 16, wherein the aggregated information at least indicates the correlation between the occurrence time and event type of the set of interactive events.

18. An information processing method, comprising: Receive the first information input by the target object to the digital assistant, the first information indicating content creation needs; as well as The digital assistant provides creative content to the target object, which is generated based on aggregated information associated with the target object. This aggregated information is generated based on historical interaction information between the target object and at least one business component. The historical interaction information is generated based on a set of interaction events between the target object and a business object within the business component, and includes a set of record entries generated based on these interaction events. Each record entry describes a corresponding interaction event and includes at least one of the following: a knowledge element describing the business object corresponding to the corresponding interaction event; an action element indicating the event type of the corresponding interaction event; and a time element indicating the time of occurrence of the corresponding interaction event. The aggregated information indicates the correlation between at least two elements in the historical interaction information, and this correlation is determined by analyzing multiple record entries corresponding to multiple interaction events.

19. The method of claim 18, wherein the aggregation information at least indicates the creation attribute information of the target object, the creation attribute information being determined based on the creation attributes of at least one business object corresponding to the set of interaction events.

20. An apparatus for information processing, comprising: A generation module is configured to generate aggregated information associated with a target object based on the target object's historical interaction information. The historical interaction information is generated based on a set of interaction events between the target object and at least one business component. The set of interaction events refers to the target object's interaction events with business objects within the business components. The historical interaction information includes a set of record entries generated based on the set of interaction events. Each record entry describes a corresponding interaction event and includes at least one of the following: a knowledge element describing the business object corresponding to the corresponding interaction event; an action element indicating the event type of the corresponding interaction event; and a time element indicating the occurrence time of the corresponding interaction event. The aggregated information indicates the correlation between at least two elements in the historical interaction information, and this correlation is determined by analyzing multiple record entries corresponding to multiple interaction events. as well as A first providing module is configured to provide the aggregated information for interaction between the target object and the digital assistant.

21. An apparatus for information processing, comprising: The determination module is configured to determine the target moment when the target object interacts with the digital assistant. as well as A second providing module is configured to provide at least one piece of content to the target object by the digital assistant, based at least on the target time. The at least one piece of content is determined based on a match between the target time and aggregated information. The aggregated information is generated based on historical interaction information between the target object and at least one business component. The historical interaction information is generated based on a set of interaction events of the target object with respect to a business object within the business component, and includes a set of record entries generated based on the set of interaction events. Each record entry describes a corresponding interaction event and includes at least one of the following: a knowledge element describing the business object corresponding to the corresponding interaction event; an action element indicating the event type of the corresponding interaction event; and a time element indicating the occurrence time of the corresponding interaction event. The aggregated information indicates the correlation between at least two elements in the historical interaction information, and the correlation is determined by analyzing multiple record entries corresponding to multiple interaction events.

22. An apparatus for information processing, comprising: The receiving module is configured to receive first information input by the target object to the digital assistant, the first information indicating content creation requirements; as well as The third providing module is configured to provide creative content to the target object by the digital assistant. The creative content is generated based on aggregated information associated with the target object. This aggregated information is generated based on historical interaction information between the target object and at least one business component. The historical interaction information is generated based on a set of interaction events between the target object and a business object within the business component, and includes a set of record entries generated based on the set of interaction events. Each record entry describes a corresponding interaction event and includes at least one of the following: a knowledge element describing the business object corresponding to the corresponding interaction event; an action element indicating the event type of the corresponding interaction event; and a time element indicating the time of occurrence of the corresponding interaction event. The aggregated information indicates the correlation between at least two elements in the historical interaction information, and this correlation is determined by analyzing multiple record entries corresponding to multiple interaction events.

23. An electronic device, comprising: At least one processing unit; as well as At least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 15, 16 to 17 or 18 to 19 when executed by the at least one processing unit.

24. 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 15, 16 to 17 or 18 to 19.

Images